Keywords: Brain-based Information Communications
Abstract: This paper describes a cybersecurity framework for protecting brain computer interface (BCI) technology. This framework consists of cybersecurity risk scenarios related to user safety/privacy and best practices to manage them. This framework provides solutions for privacy and safety issues of the existing noninvasive BCIs (e.g., electroencephalography (EEG)-based BCI). We chose to design a P300-based BCI application because it is the most popular modality, simulate some common cybersecurity attacks, and find a relevant solution to protect the user and/or integrated EEG hardware-software system. In this paper, we described how cybersecurity risks could affect BCI form streaming/recording EEG signal in real-time until sending commands. We used brain EEG Unicorn equipment and Python programing language to build our experimental paradigm, record EEG signal, classify P300 components, send a message to another user, simulate some attacks, and find perfect solutions for assuring high BCI protection. This paper gives an overview of the framework, some description of BCI hacking challenges and their impact on BCI users as well as a preliminary demonstration of a P300-based BCI system with two common simple attacks.

Keywords: Human-Machine Interface
Abstract: Brain-Computer Interfaces (BCI) show important rehabilitation effects for patients after stroke. Previous studies have also shown improvements for patients that are in a chronic stage and/or have severe hemiparesis and are particularly challenging for conventional rehabilitation techniques. For this pilot study tree stroke patients in chronic phase with hemiparesis in the lower extremity were recruited. BCI system was based on the Motor Imagery (MI) with Functional Electrical Stimulation (FES) and Avatar feedback. The results show improvements in gait and balance measured with 10 Meter Walk Test (10MWT) and Timed Up and Go Test (TUG). Walking speed for 10MWT when walking speed was measured in fast velocity improved in average for 0.16 m/s. Improvements were also measured in ankle dorsiflexion movement ability measured with Range of Motion (ROM). The findings of the current study demonstrate this kind of rehabilitation approach could be effective. However further studies are needed including more patients.

Keywords: Augmented Cognition, Human-Machine Interface, Virtual and Augmented Reality Systems
Abstract: Cognitive decline in aging is a pressing issue that can lead to long term functional impairments, including dementia. Computer-based cognitive training applications have been shown to improve cognitive skills, however, they often lack ecological validity. Researchers have proposed the use of Brain-Machine interface (BMI) systems as cognitive training tools but still face the limitation that the user cannot move freely while performing the cognitive training. Previously, we reported the successful use of a BMI system with a physical robotic third arm that allowed users to do multitasking by doing two tasks simultaneously, thereby engaging multiple cognitive skills such as attention switching, mental focus, coordination, decision making and visual information processing. In this paper, we present a cognitive training platform based on our previous multitasking paradigm with a BMI enhanced with a virtual reality experience. We conducted an experiment to investigate the efficiency of the proposed platform and monitored the level of accuracy and processing speed of the attention switching skill and compared to the traditional Attention Switching Task (AST) cognitive training paradigm. Preliminary experimental results showed that mean difference in attention accuracy scores were 3.96 s faster for the BMI-VR group compared to the AST group. Although there was a high degree of intersubject variability making the result not statistically significant, preliminary evidence reflects a potential for the proposed training approach to improve attention switching speed.

Keywords: Brain-based Information Communications
Abstract: Abstract—Magnetic resonance imaging (MRI) is one of the most important diagnostic imaging methods, which is widely used in diagnosis and image-guided therapy, especially imaging diagnosis of the brain. However, MRI images have the characteristics of low resolution, and there are limitations such as long imaging time and noise. Super-resolution techniques have been studied on three-dimensional MRI images using three-dimensional convolutional neural network. Based on some related techniques of super-resolution reconstruction of two-dimensional MRI slices, we evaluated the capability of several super-resolution technologies. We utilize the super-resolution algorithm based on generative adversarial network ESRGAN to realize super-resolution reconstruction of two-dimensional MRI slices, and then we further demonstrate that frequent details can be obtained from ESRGAN. In the aspect of two-dimensional to three-dimensional reconstruction, we use the technique of two-dimensional super-resolution on slices from three different latitudes. We rebuild reconstructed two-dimensional images into a three-dimensional form. Then based on the principle of linear interpolation, we use the surrounding effective pixel values to interpolate the null value of each slice, and realize the reconstruction of three-dimensional brain MRI.

Keywords: Human-Machine Interface, Assistive Technology, Brain-based Information Communications
Abstract: This work proposes an overview of the recent applications of brain-computer interface (BCI) technology for pediatric populations. Current BCIs have demonstrated the possibility to provide an alternative communication and interaction channel for people suffering from severe motor disabilities. However, to date research has been predominantly conducted in adults, only a few systems have been applied to pediatric population. A survey was carried out to show the ongoing trends of using BCI systems with children. We discuss three areas of applications where BCI might be helpful to children — “Communication & Control”, “BCI Gaming for Neurofeedback Training” and “Rehabilitation” — highlighting the current limitations and the possible future challenges.

Keywords: Agent-Based Modeling, Computational Intelligence, Knowledge Acquisition in Intelligent
Abstract: Time-sensitive safety-critical systems store traces as a collection of time-stamped messages that are generated while a system is operating. Analysis of these traces becomes a key task as it allows one to find faults or errors within a system that is otherwise difficult to discern, especially on complex systems. Furthermore, finding any sort of anomalous behaviours becomes critical in time-sensitive and safety-critical systems where a late detection will often lead to dire consequences. Most available approaches are generally used in networking or business processes. Thus, we are focusing on creating a lightweight and explainable approach for time-sensitive safety-critical systems.

By using a set of system traces under both normal and anomalous conditions, our approach attempts to classify whether or not a trace is anomalous. In this work, we introduce MA2DF, Multi-Agent Anomaly Detection Framework, a novel multi-agent based graph design approach for online and offline anomaly detection in system traces. Our approach takes advantage of the timing information between a sequence of events and also the event sequences itself to learn and discern between normal and anomalous traces. We have two approaches, an offline approach to discern anomalous behaviour by utilizing the event occurrence workflow graph. The other approach is an online streaming algorithm that monitors the sequence of events as they happen in real-time. This can be used to detect anomalies, find the cause, and improve system resilience. We show how our approach, MA2DF, is superior to other state-of-the-art models. The paper will explore the technical feasibility and viability of MA2DF by utilizing a case study using traces from a field-tested hexacopter.

Keywords: Agent-Based Modeling, Computational Intelligence, Machine Learning
Abstract: We consider a problem of learning decision policy from past experience available. Using the Fully Probabilistic Design (FPD) formalism, we propose a new general approach for finding a stochastic policy from the past data. The proposed approach assigns degree of similarity to all of the past closed-loop behaviors. The degree of similarity expresses how close the current decision making task is to a past task. Then it uses Bayesian estimation to learn an approximate optimal policy, which comprises the best past experience. The approach learns decision policy directly from the data without interacting with any supervisor/expert or using any reinforcement signal. The past experience may consider a decision objective different than the current one. Moreover the past decision policy need not to be optimal with respect to the past objective. We demonstrate our approach on simulated examples and show that the learned policy achieves better performance than optimal FPD policy whenever a mismodeling is present.

Keywords: Agent-Based Modeling, Expert and Knowledge-based Systems, Machine Learning
Abstract: Avoiding collision between two robot arms in a common workspace is non-trivial, since each arm acts as a dynamic obstacle for the other one. In this context, Motion Path Planning (MPP) is the process of finding an optimal and collision-free track that a robot/robot arm can follow to get to the target position starting from any point in its workspace. We propose a reinforcement learning approach to MPP for two manipulators, the first one of which tries to avoid collision with the second one. Initially, the first manipulator has no knowledge about the environment, but it successfully learns optimal collision-free paths through a Team Q-learning algorithm. We present experiments using two different methods for state discretization, namely General State (GS) Discretization and Tile Coding (TC) Discretization, as well as two different Q-learning methods, namely single-agent (SA) and multi-agent (MA) approaches.

Keywords: Agent-Based Modeling, Fuzzy Systems and Evolutionary Computing, Evolutionary Computation
Abstract: Hegselmann-Krause model plays an important role in opinion dynamics. Many researchers try to improve the classic Hegselmann-Krause model from different aspects. However, the influence of agents' media literacy on the opinion evolution always have not been taken into consideration. Due to the differences in accessing, analyzing, and producing information between agents, the media literacy gap will evidently affect their communication in real life. In this paper, media literacy is introduced to improve the traditional HK model, and a novel opinion dynamics Hegselmann-Krause model with Media Literacy (HKML) is proposed. In our work we not only consider the confidence bound, but also consider the media literacy of agents. Agents under the HKML model can select and communicate with influential neighbors through a more accuracy criterion. Numerical simulation results demonstrate that the HKML model breaks through the limit of the confidence bound, which makes more communication with less convergence time. Moreover, the HKML model shows strong robustness with the environmental noise.

Keywords: Evolutionary Computation, Agent-Based Modeling
Abstract: As people spend considerable time on digital media, online platforms have functioned as major channels for public expression. Understanding the formation and diffusion of sentiment or emotion is benefit to create a healthy environment for public discussion. In this paper, based on emotion contagion and opinion dynamics, we established a specially designed model for dynamic emotion diffusion. The method of computational modelling and simulation is applied to simulate the real-world social interactions. Factors including the distribution of initial emotion, credibility threshold, self-assertiveness and emotion decay function that might influence sentiment diffusion are analyzed, a novel concept of emotion fluctuation is introduced to predict agents' behavior. Simulation results demonstrate that all these factors mentioned above can influence the evolution of emotion, leading to its fragmentation, polarization or consensus.

Keywords: Cybernetics for Informatics, Fuzzy Systems and their applications, Optimization
Abstract: This article proposes a model calibration framework for data subject to uncertainty. Data uncertainty might be caused by a poor metrology system, measurement noise, model-form uncertainty or by the inability to directly measure the inputs and/or outputs of interest. The formulations developed, called {em Forward Maximum Likelihood} (FML) and {em Inverse Maximum Likelihood} (IML), are applicable to datasets with and without uncertainty. The FML approach performs the calibration in the space of the model's output thereby requiring repeated model simulations. Conversely, the IML approach leverages an ensemble of solutions to an inverse problem in order to perform the calibration in the space of the model's parameters. The potential loss of performance incurred by the IML approach is often justified by a sizable reduction in computational cost. In addition, we propose a chance-constrained formulation for eliminating the effects of outliers on the calibrated model. Hence, the calibration of the model and the optimal identification of outliers are performed simultaneously. This practice yields a model that increases the likelihood of most of the data in exchange for a reduction in the likelihood of a few of the worst-performing data points. Furthermore, we propose metrics for evaluating the benefit and risk of adopting the resulting model.

Keywords: Cybernetics for Informatics, Information Assurance & Intelligent, Evolutionary Computation
Abstract: Group Key Agreement (GKA) mechanisms play a crucial role in realizing various applications in different networks, such as sensor networks and the Internet of Things (IoT). To be suitable for IoT, a GKA must satisfy several critical requirements. First, a GKA must be robust against a compromised device attack and satisfy essential secrecy definitions without the existence of a Trusted Third Party (TTP). TTP is often used by IoT devices to establish ad hoc networks securely, and usually, these devices are resource-constrained. Second, the GKA must be able to distribute session keys successfully, even with offline devices. Third, a GKA must reduce the burden of heavy cryptographic computations for IoT devices. Based on these observations, we propose a new GKA scheme that satisfies all the requirements above. The proposed scheme leverages smart contracts to alleviate the computational and storage overheads on IoT devices induced by cryptographic functions. It also brings the advantage of asynchronism such that offline devices will be able to compute the group key once they are online.

Keywords: Fuzzy Systems and their applications, Cybernetics for Informatics, Computational Intelligence
Abstract: Supporting the objective of reaching consensus is a notable research area in the context of group decision making. Recently, several approaches based on an allocation of information granularity have been proposed for supporting it. Those approaches improve the consensus among the individuals participating in the decision problem by means of the required flexibility provided by the information granularity level. However, they do not take into account that the adjusted preferences could be very different from the preferences communicated by the individuals. Furthermore, they cannot be applied in decision problems where various criteria are considered to evaluate the choices. To overcome these shortcomings, we introduce a new consensus approach based on minimum adjustment for multi-criteria group decision making with an allocation of information granularity. An experimental study is also provided to illustrate this consensus approach and analyze its performance.

Keywords: Information Assurance & Intelligent, Cybernetics for Informatics, Computational Intelligence
Abstract: Uncertainty in observations about the state of affairs is unavoidable, and generally undesirable, so we are motivated to try to minimize its effect on data analysis. Detection of anomalies in data has become an important research area. In this paper, we propose a novel approach to anomaly detection based on the Variational Autoencoder method with a Mish activation function and a Negative Log-Likelihood loss function. The proposed method is validated with ten standard datasets, comparing performance on each of the various activation functions and loss functions. Experimental results show that our proposed method offers an improvement over existing methods. Statistical properties (i.e., F1 score, AUC, and ROC) of the method are also examined in light of the experimental results.

Keywords: Expert and Knowledge-based Systems, Computational Intelligence, Machine Learning
Abstract: We consider the problem of representing a multiple-criteria (i.e., multiple heterogeneous measurements) object by a single value that we can use to compare and rank different objects. An intrinsic characteristic of the multiple-criteria is their different nature (e.g., high quality and low price), and thus, the ranking process is vastly dependent on the decision-makers’ preferences and viewpoints. The different criteria denote a severe problem to find an overall value to represent the trade-offs of an object. For example, is it possible to represent the different criteria of a car by a single number and utilize this number to rank different cars in single and multiple decision-makers settings? To answer this question, we extend our proposed method to calculate a weight vector of the Ordered Weighted Average (OWA) operator based on the Laplace distribution [1] and use it to illustrate how to rank a dataset of used cars, and we compare the results with six other OWA operators. In this paper, we prove the characteristics of the new operator and illustrate its benefits in single and multiple decision-making settings. Finally, to find out how well the new OWA operator can represent the information per object; we employ the values produced by the new OWA in a regression model to estimate the used car price.

Keywords: Expert and Knowledge-based Systems, Hybrid models of NN, Computational Life Science
Abstract: Multiple Classifiers Systems (MCS) are based on the idea that the combination of the opinion of several experts can generate better results than when only one expert is used. Several MCS techniques have been developed; each one has its strengths and weaknesses depending on the context in which they are applied. This work presents a two-level sampling strategy for pruning methods that are applied to the credit scoring task. The first step of the proposal is to generate a pool using two well-known sampling methods, bagging and random subspace, that work complementarity in order to produce a diverse pool. After, a pruning method reduces the generated pool maintaining only the most competent classifiers. So, the proposal improves the MCS regarding the accuracy and the computational effort, since only a small percentage of the original pool is stored. The proposed architecture is evaluated in a credit scoring application, and the results showed that the proposed architecture obtained better accuracy rates than the single best approach and literature methods. These results were also obtained with ensembles whose sizes were around 20% of the original pools generated in the training phase.

Keywords: Expert and Knowledge-based Systems, Computational Life Science, Neural Networks and their Applications
Abstract: In this paper, we proposed a convolutional neural network called residual dense U-Net. This network is devised based on the original U-Net network. The encoder-decoder architecture in U-Net can restore the feature map to the resolution of the original image and obtain high-level semantic features. The skip-connection in U-Net can fuse the features after up-sampling and down-sampling to prevent both high-level semantic features and low-level semantic features from being lost after down-sampling. In the encoder and decoder parts, we utilize the residual dense block (RDB) from Residual Dense Network. Before each max-pooling, we replace the last convolutional layer in the original U-Net architecture with RDB. After each up-sampling, the last convolutional layer in the original U-Net architecture will also be replaced with RDB. The proposed method will be used to find poultry farms in Taiwan from satellite images. The prediction results will be evaluated using several indicators such as IOU, precision, recall, and F1-score.

Keywords: Expert and Knowledge-based Systems, Machine Learning, Neural Networks and their Applications
Abstract: We describe a novel approach to ethnobotany documentation that harnesses machine learning opportunities, specifically for the documentation of traditional ecological knowledge with mobile phones in emerging economies. Using a case study on the island of Bali as a departure point, the project maps out machine learning approaches to documentation and responds to technology and capital gradients between research contexts in the global north and south in an attempt to capture knowledge that might otherwise not be represented.

Keywords: Expert and Knowledge-based Systems, Neural Networks and their Applications, Computational Life Science
Abstract: For the epidemic prevention of avian influenza, there exist lots of differences between ideality and reality. This is why the epidemic is usually out of control. One of the reasons is that many illegal waterfowl farms are built without government registration. In this work, we proposed a new method trying to directly locate waterfowl farms, including both registered and unregistered ones without the need of human labeling. This will not only save human labors, but also update the location and size information of waterfowl farms regularly due to the computing speed of computers. In this work, we proposed a new method for satellite image augmentation. The layers of the model we proposed are not deeper than the other deep neural network models. However, we show that using the existing simple U-Net combined with residual blocks has better performance than the other deep models in this task.

Keywords: Machine Learning
Abstract: This paper presents a variational learning framework for the infinite generalized Gaussian mixture (IGGM) model. The generalized Gaussian distribution (GGD) has a proven capability in modeling complex multidimensional data due to the flexibility of its shape parameter. Infinite model addresses the model selection problem; i.e., determination of the number of clusters without recourse to the classical selection criteria such that the number of mixture components increases automatically to best model available data accordingly. We also incorporate feature selection to consider the features that are most appropriate in constructing an approximate model in terms of clustering accuracy. Experimental results on a medical application and image categorization show the effectiveness of the proposed algorithm.

Keywords: Machine Learning
Abstract: Sparse representation, collaborative representation, and other kinds of representation based classifiers have been extensively applied to face recognition. Specially, lots of experiments demonstrate that collaborative representation exhibits great potential. These existing classifiers generally focus on the single resolution. They do not work well for multiple resolution issues. However, images taken by different cameras in the real world have different resolutions. To deal with multi-resolution issues, this paper proposes a multi-resolution collaborative representation method. It builds multi-resolution training sample matrices and combines the collaborative representation to solve the multi-resolution recognition problem. Comparison experiments show that the proposed method exhibits the best comprehensive performance between all the tested methods.

Keywords: Machine Learning
Abstract: In recent times, the number of Internet of Things (IoT) devices and the applications developed for these devices has increased; as a result, these IoT devices are targeted by many malicious activities that cause potential damage in many smart infrastructures. A technique is required to appropriately classify anomalous activities to minimize the impact of these activities. The IoT networks are difficult to analyze and test because of the lack of sufficient well-structured IoT datasets for anomaly-based intrusion detection. In this paper, we present a technique we have used to generate a new Botnet dataset, from an existing one, for anomalous activity detection in IoT networks. The new IoT botnet dataset has a wider network and flow-based features. A flow-based Intrusion Detection System (IDS) can be analyzed and tested using flow-based features. Finally, we use different machine learning methods to test the accuracy of our proposed dataset. We also test the accuracy of our proposed dataset through various feature correlation and the methodology for recursive feature elimination. Our proposed IoT botnet dataset provides a ground to analyze and evaluate anomalous activity detection model for IoT networks. We have shared the newly generated Botnet dataset publicly, and a link is provided in this paper.

Keywords: Machine Learning, Agent-Based Modeling, Computational Intelligence
Abstract: Reinforcement learning is a learning paradigm in which a control is learned automatically based on rewards through trial and error based on rewards. When reinforcement learning is employed for robot control, the action that is output by reinforcement learning and the input of the actuator are often the same. A robot's actuator has a time constant of a first-order delay element between input and output. Delays result in the deterioration of the reinforcement learning performance because the environments that contain them lack the Markov property. Although there have been studies of such environments, they are problematic in that performance deteriorates when the time constant of a first-order time-delay element greater than the control cycle. The principal contribution of this paper is to propose a compensator for reinforcement learning that is more effective than conventional methods for environments with a time constant of a first-order time-delay element greater than the control cycle. The purpose of the compensator is to minimize the difference between actions in delayed environments and those not in delayed environments. Experiments reveal that the compensator increases rewards within wider ranges than conventional methods.

Keywords: Machine Learning, Image Processing/Pattern Recognition, Machine Vision
Abstract: Along with the exponential growth of online video creation platforms such as Tik Tok and Instagram, state of the art research involving quick and effective action/gesture recognition applications remains crucial. This work addresses the challenge of classifying such short video clips, using a domain-specific feature design approach, capable of performing significantly well using little training data. The method is based on Gunner Farneback dense optical flow (GF-OF) estimation strategy, Gaussian mixture models, and information divergence. We first aim to obtain accurate 3D representations of the human movements/actions through clustering the results given by GF-OF using K-means method of vector quantization. We then proceed by representing the result of one instance of each action by a Gaussian mixture model. Furthermore, using Kullback–Leibler divergence (KL-divergence), we attempt to find similarities between the trained actions and the ones in the test videos. Classification is done by matching each testing video to the trained action with the highest similarity (lowest KL-divergence). We have performed experiments on the KTH and Weizmann Human Action datasets, and the results reveal the discriminative nature of our proposed methodology in comparison with other state of the art techniques.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition, Machine Learning
Abstract: Violence and abnormal behavior detection research have known an increase of interest in recent years, due mainly to a rise in crimes in large cities worldwide. In this work, we propose a deep learning architecture for violence detection, which combines both recurrent neural networks (RNNs) and 2-dimensional convolutional neural networks (2D CNN). In addition to video frames, we use optical flow computed using the captured sequences. CNN extracts spatial characteristics in each frame, while RNN extracts temporal characteristics. The use of optical flow allows to encode the movements in the scenes. The proposed approaches reach the same level as state-of-the-art techniques and sometimes surpass them. The techniques were validated on three databases achieving very interesting results.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition, Machine Learning
Abstract: Convolutional neural networks (CNNs) for image classification can be fragile to small perturbations in the images they ought to classify. This fragility exposes CNNs to malicious attacks, resulting in safety concerns in many application domains. In this paper, we propose a simple yet efficient strategy for decreasing the effectiveness of black-box attacks that need to sequentially query the classifier network in order to build an attack. The general idea consists of applying controlled random disturbances (noise) at the softmax output layer of neural network classifiers, changing the confidence scores according to a set of design requirements. To evaluate this defense strategy, we employ a CNN, trained on the MNIST data set, and attack it with a black-box attack method from the literature called ZOO. The results show that our defense strategy: a) decreases the attack success rate of the adversarial examples; and b) forces the attack algorithm to insert larger perturbations in the input images.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition, Machine Learning
Abstract: Image hiding, as one of the most important data hiding techniques, is widely used to enhance cyber-security when transmitting multimedia data. In recent years, deep learning-based image hiding algorithms have been designed to improve embedding capacity whilst maintaining sufficient imperceptibility to malicious eavesdroppers. These methods can hide a full-size secret image into a cover image, namely full-image-to-image hiding. However, these methods suffer from a trade-off challenge to balance the possibility of detection from container image and recovery quality of secret image. In this paper, we propose a novel two-stage coverless full-image-to-image hiding method named camouflage generative adversarial network (Cam-GAN) to tackle this problem. Our method offers a hiding solution by image synthesis to avoid using any modified cover image as the image hiding container, which fundamentally breaks the error trade-off thus enhancing both the image hiding imperceptibility and the recover quality of secret images. Our experimental results also demonstrate that the proposed Cam-GAN performs better than state-of-the-art full-image-to-image hiding algorithms on both aspects.

Keywords: Neural Networks and their Applications, Machine Learning
Abstract: Terrain knowledge around unmanned ground vehicles (UGVs) is vital for autonomous navigation. Having global understanding of the surroundings of UGVs is important, although the field of view from UGVs is very limited. Thus, we utilize an aerial vehicle to provide a large terrain map from sequential aerial images. In this paper, we present multiple techniques to accelerate the process of terrain classification so that it can run onboard on the aerial platform. We evaluated our system on Jetson TX1 with actual images collected from a weather balloon which confirmed the effectiveness of the proposed system.

Keywords: Neural Networks and their Applications, Machine Learning
Abstract: The tactile properties of objects are important for robotic dexterous manipulation. An increasing number of attempts have recently been made to enable tactile information processing in robotic hand via tactile sensors. However, it remains relatively unexplored how to build tactile information processing models. In this study, we aimed to develop a spiking neural network (SNN) based on neural information processing mechanisms in sensory afferents. The SNN processes electrical signals collected from tactile sensor arrays attached to the gripper of the robotic hand while grasping objects with different shapes. We converted each of 42 -channel sensor signals from 2 arrays of 21 sensors into a spike train using the Izhikevich model, which was then fed to the SNN. The synaptic weights of the SNN were learned by the Hebbian learning through pair-based spike timing-dependent plasticity (STDP) algorithm. In addition, we implemented lateral inhibition of the second-layer neurons based on unsupervised learning similar to the one used in self-organizing maps, resulting in a winner-takes-all network. By this unsupervised learning, SNN could learn to discriminate the shape of objects via tactile sensing. In particular, it demonstrated object shape recognition with 100% accuracy. The proposed model could be useful for robots manipulating objects with tactile senses.

Keywords: Optimization, Evolutionary Computation, Computational Intelligence
Abstract: As many real-world optimization problems are large-scale and expensive, the large search space and expensive gradient computation may lead to failure of metaheuristic and classical algorithms. The problem even gets more crucial as we move from continuous domain to the discrete or mixed type one, because most of the discrete optimization problems are NP-hard and cannot be treated as convex or linear optimization, therefore there exists no cost-effective algorithm to cope with large-scale discrete global optimization (LSDGO) problems. However, due to the low memory demand and computational cost of coordinate descent (CD) search methods they are appropriate algorithms for optimizing large-scale expensive problems. In this paper, we propose a discrete version of CD algorithm called Discrete Coordinate Descent (DCD) as an effective method for solving LSDGO problems. Our proposed algorithm makes the most of two essential phases referred to as finding the region of interest and folding the search space, which shrinks it into two halves per variable and results in (1/2)^D shrinking of the whole search space at each iteration (D indicates the problem’s dimension). Since the proposed algorithm shrinks the search space rapidly, it requires a low computational budget to find the optimal value for each coordinate. In order to investigate the efficiency of our algorithm precisely, we tested it on 20 well-known large-scale problems with dimensions of 30, 50, 100, and 1000. The results demonstrate the potency of DCD not only in low-scale discrete problems, but in large-scale discrete optimization problems as well.

Keywords: Swarm Intelligence, Optimization, Machine Learning
Abstract: PSO (Particle Swarm Optimization) is attracting attention in recent years to solve the multivariate optimization problems. In PSO, multiple individuals (particles) which records its own position and velocity information are placed in the corresponding search space, and the particle swarm move to discover the optimal solution by sharing information with other particles. The search process of PSO has problem such that it is difficult to deviate from the local solution because of convergence speed of the swarms is too fast. In TCPSO (Two-Swarm Cooperative PSO), particle swarm consists of two different types of particles (a master particle swarm and a slave particle swarm) with different characteristics of search process. Experimental results of using several benchmark problems indicate that TCPSO has high performance of finding optimal solutions for multidimensional and nonlinear problems. This study introduces the concept of specificity of each master particle which indicates the diversity of master particle swarm, and proposes an algorithm that improves the efficiency of the solution search process in TCPSO by periodically analyzing the behavior of master particle swarm. This study conducts several numerical experiments for verifying the effectiveness of the proposed method.

Keywords: Machine Learning, Neural Networks and their Applications, Hybrid models of NN
Abstract: Time series is now ubiquitous and time series classification has applications in many different areas; therefore, improving the accuracy of time series classification is one of the most interesting research topics. Fully convolutional neural network (FCN) and long short term memory fully convolutional network (LSTM-FCN) are leading techniques for deep-learning-based classification models. In our previous work, we proposed a new LSTM-FCN-based model, which is called multi-channel MACD histogram LSTM-FCN (MC-MHLF). The experimental results showed the MC-MHLF model had a good classification performance. To enhance the ability of the model, we propose a new deep neural model, which is called (n, m)-Layer MC-MHLF. The (n, m)-Layer MC-MHLF model is based on the MC-MHLF model and it is composed of n LSTM layers and m convolution layers. To evaluate the (n, m)-Layer MC-MHLF model, we compared the classification performance of it with that of conventional models. The experimental results showed that the (n, m)-Layer MC-MHLF model has good performance for classifying time series.

Keywords: Evolutionary Computation
Abstract: Genetic Programming (GP) is an evolutionary method for automatic programming. In recent years, crossover operators based on the semantics of programs have attracted much attention for improving the search efficiency. We have previously proposed a semantics-based crossover that deterministically generates an optimal offspring by utilizing the target semantics explicitly in symbolic regression problems. The GP method using this crossover is called Deterministic Geometric Semantic GP (D-GSGP). However, this operation may cause rapid convergence of the population. One of the ways to maintain diversity is to use an improved selection method. epsilon-Lexicase Selection is a method to select individuals based on their responses to a part of fitness cases. D-GSGP has a high affinity with epsilon-Lexicase Selection because the responses to a part of fitness cases are components of the semantics of the program. Therefore, in this research, we combine D-GSGP and epsilon-Lexicase Selection to maintain the diversity of the population. To verify the effectiveness of our proposed method, we applied the method to a practical symbolic regression problem, the Boston Housing Dataset.

Keywords: Affective Computing
Abstract: Micro-expression (ME) recognition is an effective method to detect lies and other subtle human emotions. Machine learning-based and deep learning-based models have achieved remarkable results recently. However, these models are vulnerable to overfitting issue due to the scarcity of ME video clips. These videos are much harder to collect and annotate than normal expression video clips, thus limiting the recognition performance improvement. To address this issue, we propose a micro-expression video clip synthesis method based on spatial-temporal statistical and motion intensity evaluation in this paper. In our proposed scheme, we establish a micro-expression spatial and temporal statistical model (MSTSM) by analyzing the dynamic characteristics of micro-expressions and deploy this model to provide the rules for micro-expressions video synthesis. In addition, we design a motion intensity evaluation function (MIEF) to ensure that the intensity of facial expression in the synthesized video clips is consistent with those in real -ME. Finally, facial video clips with MEs of new subjects can be generated by deploying the MIEF together with the widely-used 3D facial morphable model and the rules provided by the MSTSM. The experimental results have demonstrated that the accuracy of micro-expression recognition can be effectively improved by adding the synthesized video clips generated by our proposed method.

Keywords: Affective Computing, Human Performance Modeling, Human-Computer Interaction
Abstract: This paper provides a new TB-APR approach, using a projective test to build a corpus. The research of Personality Computing shows that it is possible to recognize personality automatically from texts (TB-APR), using paradigms of supervised learning. As concerns these paradigms, texts need to be labeled by psychometric instruments and, in order to realize this task, personality inventories are used. Personality inventories display great facilities for application and correction, but they do not evince efficient ways of controlling intentional or non-conscious omissions of undesired personality characteristics by the individual, which may explain the low correlations found in literature regarding TB-APR models. In this article, we propose the labeling of a textual corpus using the Z-test projective instrument, in order to mitigate the limitations of inventories, since it is very sensitive and offers the possibility of collective application. The proposed model used bag-of-words techniques, with some state of art machine learning inductors. The results are promising, with AUC-ROC on 0.85 average.

Keywords: Affective Computing, Human-Computer Interaction
Abstract: This paper introduces a new ROSbag-based multimodal affective dataset for emotional and cognitive states generated using the Robot Operating System (ROS). We utilized images and sounds from the International Affective Pictures System (IAPS) and the International Affective Digitized Sounds (IADS) to stimulate targeted emotions (happiness, sadness, anger, fear, surprise, disgust, and neutral), and a dual N-back game to stimulate different levels of cognitive workload. 30 human subjects participated in the user study; their physiological data were collected using the latest commercial wearable sensors, behavioral data were collected using hardware devices such as cameras, and subjective assessments were carried out through questionnaires. All data were stored in single ROSbag files rather than in conventional Comma-Separated Values (CSV) files. This not only ensures synchronization of signals and videos in a data set, but also allows researchers to easily analyze and verify their algorithms by connecting directly to this dataset through ROS. The generated affective dataset consists of 1,602 ROSbag files, and the size of the dataset is about 787GB. The dataset is made publicly available. We expect that our dataset can be a great resource for many researchers in the fields of affective computing, Human-Computer Interaction (HCI), and Human-Robot Interaction (HRI).

Keywords: Affective Computing, Human-Machine Interface
Abstract: Research in social psychology has extensively shown that in cohesive groups, individuals often mirror each other's prosody, facial expressions, and body movements. This mirroring effect can help determine the level of comfort or the extent of engagement and genuine interest between two or more interlocutors. In this work, using an annotated dataset consisting of videos of three-person conversations, we aim to analyze the extent of rapport in each of the triadic groups. We generate behavioral curves from features extracted from the participants' face and body movements. These are the sampled time series signals resulting from their multimodal features. Next, the extents of synchrony are analyzed by aligning the behavioral curves of pairs of participants. The alignment tests show that basic correlation coefficient measures outperform more advanced curve matching techniques when used to estimate the similarities between multidimensional behavior curves. They also show that in this dataset, synchrony is better observed from facial expressions than body movements. For this reason, using facial action units, we show that an end-to-end recursive neural network (RNN) trained using a regression loss yields good results in predicting the extent of synchrony in small groups.

Keywords: Affective Computing, Wearable Computing
Abstract: Machine learning based acute stress detection systems use physiological sensor data to objectively predict acute stress. However, machine learning algorithms developed for stress detection do not consider how machine learning algorithm performance may be affected based on a change(s) in the deployment environment. In this study, the deployment environment changes that are investigated are sensor type and sensor placement. Electrodermal activity (EDA) and skin temperature (TEMP) data from two different sensors, the RespiBAN Professional (RespiBAN) and the Empatica E4 are used to train three different machine learning models. The RespiBAN records the EDA data from the rectus abdominis and records the skin TEMP data from the sternum. The Empatica E4 sensor records both EDA and skin TEMP data from the wrist. Three different support vector machine (SVM) models were trained to classify no-stress versus stress states using EDA and skin TEMP data. The first model was trained using data from the RespiBAN wearable sensor (SVM-R), the second model was trained using data from the Empatica E4 sensor (SVM-E) and third model was trained using data from both sensors (SVM-RE). The accuracy of SVM-R on a test set recorded by the RespiBAN sensor was 100%. The accuracy of SVM-E on a test set recorded by the Empatica E4 sensor was 99%. The accuracy of SVM-RE on a test set recorded by both the RespiBAN and Empatica E4 sensor was 82%. The accuracy of the SVM-R on a test set recorded by the Empatica E4 was 64%. These results suggest that research and development cannot be hardware or placement agnostic with wearable sensing data and sensor type and placement must be taken into consideration when reporting performance metrics of physiological based stress detection machine learning algorithms.

Keywords: Human-Machine Interface, Information Visualization, Virtual and Augmented Reality Systems
Abstract: Due to the challenges of autonomous driving, for the near future, automated vehicles will not be able to drive in all conditions without any human intervention. The challenge arises when no human driver is inside the vehicle to resolve the challenging situation. One solution for this might be teleoperation, here a remote operator takes control over the car and resolves the situation from a distance. But teleoperation technology itself comes with certain challenges, one of them being creating a good situational awareness at the operator site based on the sensor data transmitted from the automated vehicle. To understand this challenge better, in this paper a five-week long-time study is conducted with the goal of measuring the impact of different displays, video-canvases and -streaming quality on situation awareness, workload and decision making. The objective results show a significant impact of video streaming quality on various factors of situation awareness. On the other hand the subjective results such as workload, immersion, usability and presence indicate that video streaming quality only has an impact in situations with high contrasts and over all scenes the impact of video quality on subjective satisfaction is not significant. Between the three display modes no significance regarding quality was found. However, the participants preferred the head mounted display over the other options even though the results indicate that the head mounted display is most sensitive to changes in video streaming quality.

Keywords: Human-Machine Interface, Brain-based Information Communications
Abstract: Human-Swarm interaction has attracted a lot of attention for their applications in areas such as exploration, rescue, surveillance, and interplanetary exploration. When humans assume a supervisory or tactician role in managing the robot swarm, the humans' (physiological) state significantly affects the mission performance. In this work, we explore the physiological correlates with the user's tactical decisions in a simulated search and rescue mission. The mission consists of supervising three groups of unmanned aerial vehicles and three groups of unmanned ground vehicles to search for a target building. The mission complexity is increased by introducing static adversarial teams. Due to the adversarial team's presence, the user should employ different tactics to search for a target. While the user interacts with the swarm, brain activity in forms of electroencephalogram (EEG) and eye movements are recorded. 20 participants, with prior experience in playing real-time strategy games, took part in the study. A linear mixed effect model is used to study the correlated physiological features and tactical decisions. Six features are extracted from the physiological data: engagement level, mental workload, Fz-Pz coherence, Fz-O1 coherence, pupil size, and the number of gaze fixations. The results show that mental engagement and Fz-O1 coherence are the important factors in predicting the tactical decisions. Specifically, Fz-O1 coherence in Beta (22.5-30 Hz) and Gamma (38-42 Hz) band is found to be significant.

Keywords: Human-Computer Interaction, Virtual and Augmented Reality Systems, Information Visualization
Abstract: Unilateral spatial neglect (USN) is a higher cognitive dysfunction that can occur after a stroke. It is defined as an impairment in finding, reporting, reacting to, and directing stimuli opposite the damaged side of the brain. We have proposed a system to identify neglected regions in USN patients in three dimensions using three-dimensional virtual reality. The objectives of this study are twofold: first, to propose a system for numerically identifying the neglected regions using an object detection task in a virtual space, and second, to compare the neglected regions during object detection when the patient's neck is immobilized (‘fixed-neck’ condition) versus when the neck can be freely moved to search (‘free-neck’ condition). We performed the test using an immersive virtual reality system, once with the patient's neck fixed and once with the patient's neck free to move. Comparing the results of the study in two patients, we found that the neglected areas were similar in the fixed-neck condition. However, in the free-neck condition, one patient's neglect improved while the other patient’s neglect worsened. These results suggest that exploratory ability affects the symptoms of USN and is crucial for clinical evaluation of USN patients.

Keywords: Human-Machine Interface, Assistive Technology, Human-Computer Interaction
Abstract: Wearable robotic devices are being designed to assist the elderly population and other patients with locomotion disabilities. However, wearable robotics increases the risk from falling. Neuroimaging studies have provided evidence for the involvement of frontocentral and parietal cortices in postural control and this opens up the possibility of using decoders for early detection of balance loss by using electroencephalography (EEG). This study investigates the presence of commonly identified components of the perturbation evoked responses (PEP) when a person is in an exoskeleton. We also evaluated the feasibility of using single-trial EEG to predict the loss of balance using a convolution neural network. Overall, the model achieved a mean 5-fold cross-validation test accuracy of 75.2 % across six subjects with 50 % as the chance level. We employed a gradient class activation map-based visualization technique for interpreting the decisions of the CNN and demonstrated that the network learns from PEP components present in these single trials. The high localization ability of Grad-CAM demonstrated here, opens up the possibilities for deploying CNN for ERP/PEP analysis while emphasizing on model interpretability.

Keywords: Kansel (sense/emotion) Engineering, Information Visualization, Human Factors
Abstract: This study proposes a fast high dynamic range imaging (HDRI) technique for light measurement to shorten the long capturing time of current camera-aided computational photography widely used in lighting practice. In comparison with the conventional meter measurement, HDRI-assisted lighting measurement is a remote, efficient, affordable yet time-consuming method. The fast HDRI technique increases the film speed (ISO) to speed up the process taking a sequence of low dynamic range images. Since increasing camera’s film speed may introduce more image noise, the possible error rate of the proposed method is evaluated by applying Gaussian noise estimation and impulsive noise detection on the image with different film speeds. In addition, a new per-pixel calculation process is developed to retrieve the illuminance of a target scene with selected regions of interest, which can be used to assist human-centric lighting tasks. Extensive comparative experiments are also conducted to verify the accuracy and efficiency of the proposed method.

Keywords: Human-Computer Interaction, Human-Machine Cooperation and Systems
Abstract: Data exfiltration is a serious threat to organizations. Such exfiltrations cause breach events that can lead to millions of dollars of loss. Perimeter defense is not enough by itself since successful exploits from insiders can also be very damaging. Internal network user activities need to be monitored to detect malicious actions. Automatic machine learning methods can be applied for network anomaly detection, but they create a lot of false alarms. Domain experts can identify malicious users, but they are unable to process large volumes of data. Interactive machine learning (iML) deals with this tradeoff by creating an efficient collaboration between domain experts and machine learning algorithms. Previous research in iML has focused mainly on collaboration with non-experts. The design and requirements for expertise-driven iML have yet to be delineated for cybersecurity applications. In this research, we proposed an Active Learning (AL) model trained with outputs from a liberal (outputting many false alarms as well as possible hits) anomaly detection (AD) criterion to study expert-iML collaboration in anomaly detection. The results showed that: iML in this context can prune false alarms and minimize misses; the performance/compatibility tradeoff that typically occurs in conventional machine learning updates may be less salient in iML. We suggest that compatibility between experts and algorithms can be improved by presenting information about feature relevance during the training process.

Keywords: Human-Computer Interaction, Human-Machine Cooperation and Systems, Human Factors
Abstract: The use of machine learning algorithms is surging in industrial condition-based maintenance systems. However, machine learning algorithms are often considered a black box undermining the adoption of these systems by creating human-automation interaction challenges. To address this opacity issue, we must explain and describe the logic and outcome of the algorithms (known as explainability and transparency). Existing design practices are not effective in meeting these requirements; thus, more user-based experiments should be conducted to identify effective design practices. Experimental platforms that support the empirical validation of transparency and explainability approaches are extremely limited both in academia and industry. We propose an open-source platform to assist researchers in conducting human-subjects experiments.

Keywords: Human-Computer Interaction, Human-Machine Interface, Human Factors
Abstract: Connected-Autonomous Vehicles (CAV) is an emerging and fast-paced transportation field where diverse companies, as traditional transportation companies and software companies, compete for dominance. CAV’s benefits are promising, and this has led to an increasing interest in the literature. Despite different levels of autonomy, people might stay (to some extent) on the control of CAV, because full autonomy remains rare in transportation. Consequently, human errors are vulnerabilities that remain as potential reasons for malware infections in CAV. Usability becomes a vital attribute to mitigate the occurrence of such errors or prevent them from occurring. We aimed to understand users' expectations of privacy towards CAV's most autonomous levels, part of users' satisfaction and CAV's usability. Our survey gathered 50 responses, among 40 vehicle owners and ten non-owners. Responses showed six tendencies of users' behavior about CAV and its privacy issues. From the tendencies, we discuss implications for the design of CAV for future works.

Keywords: Human-Machine Cooperation and Systems, Human-Machine Interface, Human Factors
Abstract: Humans often have difficulty accomplishing tasks in correspondence with automation with concealed inner workings. Researchers suggest that allowing humans to see into the inner workings of automation will lead to better understanding, trust in, reliance on, joint task completion with, and better situation awareness of the automation. We identified and compared four transparency models that assist researchers in designing and conducting empirical studies by guiding them on what, how, and when information on or about automation should be disclosed. The results of this review will assist researchers with understanding, identifying, and employing suitable transparency models to their applications.

Keywords: Mental Models, Human Performance Modeling, Human Factors
Abstract: In recent times, several marine accidents have occurred because of human errors. Mental workload is considered as one of the causes of human errors. The physiological index such as heart rate, nasal temperature, brain wave and saliva are commonly used to measure mental workload. Among these, we focus on nasal temperature as it can measure mental workload without contacting subjects. However, measuring nasal temperature is time-consuming because of the manual detection of the nasal position in infrared (IR) images. This study proposes an automatic method for the measurement of nasal temperature based on the combination of motion-sensing devices and an IR camera. Based on experiments conducted using simulators, the automatic measurement of nasal temperature using both motion-sensing devices and an IR camera has been demonstrated. It is necessary to adjust the coordinate system of the motion-sensing devices and IR camera to accurately measure nasal temperature.

Keywords: Robotic Systems, Bio-mechatronics and Bio-robotics Systems, Model-based Systems Engineering
Abstract: The purpose of this paper is to propose a new type of a kinetic chained walking robot capable of walking with only a single actuator, and is to design its trajectory tracking control system. Legged robots are able to move across irregular terrains, however, have an issue on energy efficiency compared with other morphology. A bio-inspired approach often provides effective solutions, for example, a lizard is able to mainly walk by utilizing only twisting its waist. To mimic this characteristic by robotics, a robot consisting of four-bar linkage mechanism is proposed. This idea improves simplification of its locomotion analysis. In this paper, two important kinematics characteristics are analyzed in order to propose locomotion ability and effectiveness of the robot. In particular, a turning angle and a stride distance are analysed. After that, a trajectory tracking control system is designed based on the PID control low. Ideas for the control system design in this paper are both to decide an bias of an input angle function as a input of the system and to set a control period on half period of the input angle function. Finally, effectiveness of the designed control system is verified via numerical simulations. A straight line and a circle trajectory are adopted for the verification. As the results, it is shown that the designed trajectory tracking control system is capable of tracking two different trajectory. In addition, it is also shown that the designed trajectory tracking control system satisfies the kinematics analysis results from the side of view of the kinematic of the robot.

Keywords: Medical Mechatronics, Bio-mechatronics and Bio-robotics Systems
Abstract: Tissue classification from electrical impedance spectroscopy has several applications in diagnosis, surgical planning, and minimally invasive surgery. The method involves applying an alternating current to the sample and measuring its electric impedance at various frequencies. The spectrum is fit to a equivalent electric circuit that mimics the shape of the tissue’s impedance spectrum. The model parameters are then used for classification.

This paper proposes a new solution to decompose the model fitting problem into a form suitable for multi-objective optimisation, from which all the non-dominated solutions are used to form the database of parameters for a given tissue, as opposed to a single solution that is typically seen in impedance spectroscopy.

The solution explores the use of the reference point dominance condition within Non-dominated Sorting Genetic Algorithm II to fit the data to the double dispersion Cole model. Each nondominated solution contain values for the dispersion model elements. The multiple parameter value solutions from the optimiser are used as features in a weighted Naive Bayes classifier to identify a new tissue sample. Experiments results in 3 different tissue samples shows that the method is successful in correctly labelling the data with an average accuracy of 89%.

Keywords: Intelligent transportation systems, Bio-mechatronics and Bio-robotics Systems, Intelligent Assistants and Advisory Systems
Abstract: Driving a car is a complex and potentially risky activity in people's everyday life and it requires the full involvement of physiological and cognitive resources. Any loss of these resources can cause traffic accidents. For example, drowsy driving affects the ability to adapt, predict, and react to unexpected events. A solution to this problem is the adoption of Advanced Driver Assistance Systems (ADAS), which can warn the driver if sleepiness is detected. Thus, they should include a Driver Monitoring System (DMS) to understand, measure, and monitor human behaviour in different scenarios. This article is focused on detecting driver drowsiness by using non-intrusive measures such as the behavioural approach, as it is the most promising solution to use in real vehicles. The developed framework allows the extraction of drowsiness-related measures by analysing the driver's face with a standard camera. First, a face detection stage identifies the driver's face in a video frame. Then, a set of facial landmarks locations are identified. These landmark points are used to estimate the head orientation and to detect when a blink occurs. By monitoring properly defined ocular variables, the degree of driver drowsiness is detected through a Fuzzy Inference System (FIS).

Keywords: Robotic Systems, Bio-mechatronics and Bio-robotics Systems, Intelligent Learning in Control Systems
Abstract: Due to the harsh and unknown underwater environment, the question of how autonomous underwater vehicles (AUVs) should navigate and maneuver, especially in a dynamic environment with changing flow patterns, is still largely open. This paper presents a systematic background flow sensing framework, which plays an important role in improving the navigation/control intelligence of AUVs. This flow sensing framework utilizes distributed pressure measurements of AUVs to estimate surrounding flow fields. The proposed method first determines the flow pattern/model around AUVs based on fast Fourier transform (FFT) spectrum analysis and then uses recursive Bayesian estimation and dynamic mode decomposition (DMD)-based modeling to identify model parameters. This method is capable of sensing background flow fields even in flow pattern changing environments, e.g., open waters in real-world scenarios, thus dramatically expanding the application scope of the existing flow sensing methods. Simulation results are provided to demonstrate the effectiveness of the proposed flow sensing method.

Keywords: Robotic Systems, Bio-mechatronics and Bio-robotics Systems
Abstract: Safe yet stable grasping requires a robotic hand to apply sufficient force on the object to immobilize it while keeping it from getting damaged. Soft robotic hands have been proposed for safe grasping due to their passive compliance, but even such a hand can crush objects if the applied force is too high. Thus for safe grasping, regulating the grasping force is of uttermost importance even with soft hands. In this work, we present a force controlled soft hand and use it to achieve safe grasping. To this end, resistive force and bend sensors are integrated in a soft hand, and a data-driven calibration method is proposed to estimate contact interaction forces. Given the force readings, the pneumatic pressures are regulated using a proportional-integral controller to achieve desired force. The controller is experimentally evaluated and benchmarked by grasping easily deformable objects such as plastic and paper cups without neither dropping nor deforming them. Together, the results demonstrate that our force controlled soft hand can grasp deformable objects in a safe yet stable manner.

Keywords: Cooperative Systems, Distributed Intelligent Systems, Intelligent Power and Energy Systems
Abstract: Home energy management plays a key role in demand response for residential customers to reduce the total cost via scheduling household loads energy consumption. However, excessive energy consumption by customers will bring a great challenge to the stability of the grid. To address the challenge, a day-ahead multi-agent reinforcement learning method is proposed for home energy management under a peak powerlimiting. We first formulate the total cost minimization problem as a Markov game, and then a novel household loads energy consumption scheduling algorithm is proposed based on Mutilagent Deep Deterministic Policy Gradient (MADDPG). It is worth mentioning that the proposed algorithm can achieve cooperation between agents so that it can meet the peak power-limiting constraint. Simulation results are provided in this paper to show the effectiveness of the proposed method.

Keywords: Cooperative Systems
Abstract: One of the typical autonomous driving systems is a human-machine cooperative system that intervenes in the driver operation. The existing system does not tolerate driver individualities. As such, some drivers will be less accepted due to personal preferences do not match a single and public driving style. Therefore, an autonomous driving needs to make consideration of the driver individuality in addition to safety. This paper considers a human-machine cooperative system balancing safety with the driver individuality using the Human-In-The-Loop System (HITLS). This paper assumes that it is safe for HITLS to follow the target side-slip angle and target angular velocity without conflicts between the controller operation and the driver operation. The target system is rear-wheel steering control. In this paper, we propose HITLS using the primal-dual algorithm and the internal model control (IMC) type I-PD controller as the rear-wheel steering control system framework which reflects the driver individuality and an implementation way of this HITLS. HITLS can consider that it be able to reflect the driver individuality in control using a human operation as degrees of freedom. In HITLS, the signal expander delimits the human-selectable operating range and the internal model controller cooperates stably the human operation and automated control in that range. The primal-dual algorithm is used as the driver model and the signal expander of HITLS. The IMC type I-PD controller is used for giving a servo characteristic. The outcomes of this research are the making of the rear-wheel steering system which converges to the target value while reflecting the driver individuality.

Keywords: Cooperative Systems, Intelligent Assistants and Advisory Systems
Abstract: Decreasing birth rates and an aging population in society often cause labor shortages in the manufacturing industry, making the development of methods to improve productivity based on limited human resources imperative. One way to achieve this is by enhancing product quality via the reduction of product losses and the consequent need for reassembly due to human error. Human error during assembly can arise from specific actions via the arms and fingers. We assumed that these errors can be captured based on the information on human skeletal models. The purpose of this study is to propose and develop a system that acquires information about assembly procedures by using human skeletal models, including the fingers of workers, and notifies them of skipped procedures and errors in part types. Further, we confirm the basic capability of the proposed system via experiments based on simulated assembly work. The proposed system monitors workers' motion based on color and depth images captured by a single RGB-D camera. In addition, we developed a function to detect the process and to point out errors with audible and visual feedbacks when errors were made by workers in assembly processes. In the experiment using simulated assembly work, the proposed system exhibited an accuracy rate of 98.3% with respect to acquisition of assembly processes. In the case of an error in an assembly process, the system was able to point out the error correctly and provide feedback to the worker before he had finished picking up the wrong part. In conclusion, we confirmed that the developed system exhibited the basic capability to acquire work procedures and efficiently point out errors in real time.

Keywords: Cyber-Physical Cloud Systems, Distributed Intelligent Systems, Cooperative Systems
Abstract: Traditional lighting systems suffer from the problem of low energy efficiency and low illumination quality due to its disappointing management. To address this issue, in this paper, a novel traffic-flow adaptive scheme of smart lighting system is proposed on the basis of the cyber-physical cloud system. The cyber-physical cloud system consists of the digital twin and cyberphysical system. The operation of lighting system is simulated in the counterpart twin system with the digital twin technology. The cyber-physical system realizes data collection, information interaction, analysis and processing, as well as complex computation and remote control. The traffic adaptive scheme works according to brightness sequence to improves the energy efficiency of lighting system and provide higher illumination quality for drivers. Extensive simulation results verify the proposed control scheme could improve the energy efficiency of the lighting system.

Keywords: Enterprise Architecture & Engineering, Enterprise Information Systems, Distributed Intelligent Systems
Abstract: This paper describes an auto scale approach, drived on the use of environment metrics to scale applications. On high granularity application environments, every application impacts directly in another applications. The main goal of this paper is to predict dependencies scale demands before this application becomes already compromised by overload.

Keywords: Distributed Intelligent Systems, Intelligent Learning in Control Systems
Abstract: ‎In this paper‎, ‎a deceptive version of guarding a territory in a grid world is proposed‎. ‎Like the original version‎, ‎a defender tries to intercept an invader before it invades the targets‎. ‎However‎, ‎the discerning invader can deceive the defender about its real goal so that it can improve its performance‎. ‎On the other hand‎, ‎the defender tries to‎ ‏‎confront the invader by guessing its true goal‎. A two-level policy is obtained via reinforcement learning (RL)‎. ‎In the lower level, the ‎invader and the defender learn their optimal policies to invade or defend a particular territory‎‎. ‎In the higher level, ‎the invader learns which territory it should pretend to invade ‎in order to manipulate the defender's belief function‎‎. A multiagent reinforcement learning (MARL) algorithm is implemented for obtaining the optimal policies ‎via the minimax Q-learning algorithm at the lower level. Whereas for the higher-level policy a single-agent Q-learning algorithm is utilized. ‎Results of different reward functions are compared. ‎The results show that the invader can improve its performance by taking advantage of deception‎‎‎.

Keywords: Model-based Systems Engineering, Distributed Intelligent Systems
Abstract: Describing an image with natural sentence without human involvement requires knowledge of both image processing and Natural Language Processing (NLP). Most of the existing works are based on unimodal representations of the visual and textual contents using an Encoder-Decoder (EnDec) Deep Neural Network (DNN), where the input images are encoded using Convolutional Neural Network (CNN) and the caption is generated by a Recurrent Neural Network (RNN). This paper dives into a basic image captioning model to quantify the impact of multimodal representation of the visual and textual cues. The multimodal representation is carried out via an early fusion of encoded visual cues from different CNNs, along with combined textual features from different word embedding techniques. The resultant of the multimodal representation of the visual and textual cues are employed to train a Long Short-Term Memory (LSTM)-based baseline caption generator to quantify the impact of various level mutation of the complementary features. The ablation study involved with two different CNN feature extractors and two different textual feature extractors, shows that exploitation of the complementary information outperforms the unimodal representations significantly with endurable timing overhead.

Keywords: Distributed Intelligent Systems, Model-based Systems Engineering
Abstract: Network virtualization recognized as an enabling technology for the forthcoming networks is utterly popular. One of the main challenges of network virtualization is called the virtual network embedding problem. Virtual network embedding (VNE) aims to allocate a set of virtual machines onto a set of interconnected physical hardware in the cloud computing environment. Traditional exact solutions, considered as a time-consuming process to achieve a global optimal solution, have been proofed to be mathcal{NP}-hard. On the other hand, some existing heuristic solutions tend to decouple VNE problems into two stages: virtual node mapping (VNoM) and virtual link mapping (VLiM). Undoubtedly, these kinds of decomposition would result in low acceptance ratio and inefficient substrate resource utilization.

In this paper, we propose a distributed parallel Genetic Algorithm combined with graph theory for solving VNE in one-stage. Our proposed algorithm achieves better performance than previous baseline solutions while meeting the stringent time requirements for online VNE problems.

Keywords: Distributed Intelligent Systems, Model-based Systems Engineering
Abstract: This paper presents a new robust fault detection and isolation (FDI) strategy for distributed and decentralized systems. Such a system consists of several interconnected subsystems. A novel FDI system architecture is designed for these systems. Each subsystem is assigned to a local fault detector performing a part of the overall fault detection algorithm. Fault isolation is performed in a separate global fault isolator. Consistency-based methods based on state-set observation are used for robust FDI. Moreover, this paper introduces a faster fault isolation. For this, the search-space containing all fault candidates is split. Possible network effects in the communication between the computing units are also considered. A simulation example of a three-tank system is used to illustrate the effectiveness of this FDI strategy.

Keywords: Distributed Intelligent Systems, Decision Support Systems, Infrastructure Systems and Services
Abstract: Drone susceptibility to jamming or spoofing attacks of GPS, RF, Wi-Fi, and operator signals presents a danger to medical delivery systems. A detection framework capable of sensing attacks on drones could provide the capability for active responses. The identification of interference attacks has applicability in medical delivery, disaster zone relief, and FAA enforcement against illegal jamming activities. A gap exists in the literature for solo or swarm-based drones to identify radio frequency spectrum attacks. Any non-delivery specific function, such as attack sensing, added to a drone involves a weight increase and additional complexity; therefore, the value must exceed the disadvantages. Medical delivery, high-value cargo, and disaster zone applications could present a value proposition that overcomes the additional costs. The paper examines types of attacks against drones and describes a framework for designing an attack detection system with active response capabilities to improve the reliability of delivery and other medical applications.

Keywords: Infrastructure Systems and Services, Service Systems and Organization, Cyber-Physical Cloud Systems
Abstract: Cloud-based architectures have grown in recent years, especially the interest in container-based solutions has sharply increased by enterprises worldwide. Containers are a form of lightweight virtualization that can be used to provide cloud services, and the adoption of this kind of technology in a bare-metal context is becoming strong because they can offer many benefits, like performance efficiency and costs reduction. Docker is a widespread platform for the creation and management of containers. As in any computational cloud service, Docker environments must deal with the intensive workload and may have a long-term life cycle, characteristics that might trigger some problems that compromise the system dependability. The phenomenon of software aging is one of these likely problems. It is a process of cumulative errors or system misbehavior that leads to application failures and performance degradation throughout its runtime. This paper aims at monitoring and evaluating software aging effects experienced by the Docker platform in a cloud computing environment. We conducted two experimental studies with automated workloads to simulate the life cycle of containers and to simulate the intensive use of Docker features, while the system was monitored. The results show high resource consumption as RAM and CPU usage in the operating system's network utility, in addition to memory fragmentation in the sub-processes of the Docker platform. Trends of increasing resident memory consumption were also observed in one of these scenarios.

Keywords: Intelligent Green Production Systems, Service Systems and Organization, Decision Support Systems
Abstract: Timely and proper recycling of end-of-life products promotes the sustainable development of our human society. Cost-effective and energy-efficient disassembly is a key step to realize such recycling. A disassembly process is usually uncertain because of different quality of subassemblies in an end-of-life product. This work considers resource constraints and operation failure in such a process. A novel mathematical model is formulated with the objectives to maximize profit, minimize energy consumption, and minimize the total need for disassembly resources. A new solution method called a multi-objective discrete migratory bird optimizer is proposed to solve it. We successfully verify its effectiveness and feasibility via a product disassembly example. Its superiority over the well-known nondominated sorting genetic algorithm II and a multi-objective grey wolf optimizer is experimentally demonstrated.

Keywords: Enterprise Information Systems, Enterprise Architecture & Engineering, Decision Support Systems
Abstract: This paper solves the problem of correcting database completion rules, imputing missing rule conditions, and executing them interactively and efficiently. Often in real-world scenarios, database completion rules have syntactic errors. Even after correcting these rules, the process of correction can introduce spurious rule conditions that can result in inefficient rule execution. We solve this problem by leveraging programming-by-example data transformations, sketching data structures such as bloom filters, and leveraging entity resolution rules. The paper proposes to use programming-by-example data transformations along with reducing the size of examples generated for it. We build upon current work to involve the user in the process of making PBE examples. The paper also proposes to use sketching data structures for the database completion process under dynamic rules, along with reducing their numbers and sizes of them. We again build upon existing work to involve the user in the process of making a summary on an incomplete database, which also increases efficiency. The paper also proposes to efficiently leverage entity resolution rules to find missing rule conditions in database completion rules.

Keywords: Infrastructure Systems and Services, Model-based Systems Engineering
Abstract: The elastic optical networks have shown promise for future of optical communications supporting high transmission rates data. To meet high transmission rates, you need to solution RMLSA (Routing, Modulation Level, Spectrum Assignment) problem which is to select a route, choose a modulation level and a range of free spectrum. A new algorithm called Circuit Interference Reduction - Minimum Allocation Slots (CIR-MAS) is presented in this work. This algorithm seeks to select a modulation format that is more resistant circuit interferences (established circuits on the networks). Also it selects a route with the minimum allocation slots among the alternative routes, in order to reduce the blockage caused by degradation of circuits. The performance of the CIR-MAS algorithm was evalueted on the NSFNet and EON topologies by comparing with the following algorithms: K-Shortest Path Computation (KS-PC), Modified Dijkstra Path Computation (MD-PC) and K-Shortest Path with Reduction of QoTO (KSPRQoTO), wich have already been presented in the literature. The CIR-MAS algorithm presented a minimum gain of 40.5% in terms of circuit blocking probability, and in terms of bandwidth blocking probability, it obtained a minimum gain of 37.5% when compared all competing algorithms.

Keywords: Grey Systems, Model-based Systems Engineering, Smart urban Environments
Abstract: This paper proposes a research framework for social impact assessment of the construction land reduction project, a unique brownfield redevelopment project in China. This paper explains the steps of analyzing the social impact assessment of the construction land reduction project, including the identification of the indicator dimension by the word frequency statistical method, the initial indicator system determined by the literature analysis method, the final indicator system obtained by the Delphi method screening, and the indicator weight determined by the entropy combination weight method, etc. Then a grey clustering model for social impact assessment of the construction land reduction project is established. Finally, a numerical example is applied to show feasibility of the framework. This research is expected to put forward suggestions and countermeasures for the implementation of similar projects through the social impact assessment of the construction land reduction project. And the assessment indicator system and evaluation model constructed in this paper can provide reference for the social impact evaluation of similar projects in the future.

Keywords: Intelligent transportation systems
Abstract: Vehicle-to-vehicle communication is a solution to improve the quality of on-road traveling in terms of throughput, safety, efficiency and comfort. However, road users that do not communicate their planned activities can create dangerous situations, so prediction models are needed to foresee and anticipate their motions in the drivable space. Various prediction methods exist, either physics-based, data-based or hybrids, but they all make conservative assumptions about others' intentions, or they are developed using unrealistic data, and it is unclear how they perform for trajectory prediction. In this work, we introduce and demonstrate an optimal hybrid framework that overcomes these limitations, by combining the predictions of several physics-based and data-based models. Using on-road measured data we show that this novel framework outperforms the individual models in both longitudinal and lateral position predictions. We also discuss the required prediction boundaries from a safety perspective and estimate the accuracies of the models in relation to automated vehicle functions. The results achieved by this method will enable increased safety, comfort and even more proactive reactions of the automated vehicles.

Keywords: Intelligent transportation systems
Abstract: Reduced alertness due to the drowsy state that impairs driving performance has been reported to be one of the significant causes of road accidents. This paper aims to present a data fusion of vehicle-based and ECG signals for classifying three levels of driver drowsiness, including alert, moderately drowsy, and extremely drowsy. Lateral deviation from the road centerline, steering wheel angle, and lateral acceleration are employed as vehicle-based signals. Two ECG leads are also exploited to collect heart rate variability of drivers. Thirty-nine features from vehicle-based data and ten features from heart rate variability signals are extracted. Finally, k-nearest neighbors and random forest are used as classifiers to classify the level of drowsiness using selected features by the sequential feature selector. Age and gender, as the two most effective human factors, are considered to assess the performance of the method in different age/gender groups. The proposed method is evaluated on experimental data that were collected from 93 manual driving tests using 47 different human volunteers in a driving simulator. Results show that hyperparameter-optimized random forests obtain an accuracy of 82.8% for the detection of drowsiness levels based on vehicle signals only, and an accuracy of 88.5% based on ECG derived data only. Data fusion of ECG signals and vehicle data improves the accuracy of classification to 91.2%. The model performs slightly better on older than on younger drivers, but no gender difference was found.

Keywords: Intelligent transportation systems
Abstract: In this article, the authors present a novel method to learn the personalized tactic of discretionary lane-change initiation for fully autonomous vehicles through human-computer interactions. Instead of learning from human-driving demonstrations, a reinforcement learning technique is employed to learn how to initiate lane changes from traffic context, the action of a self-driving vehicle, and in-vehicle user’s feedback. The proposed offline algorithm rewards the action-selection strategy when the user gives positive feedback and penalizes it when negative feedback. Also, a multi-dimensional driving scenario is considered to represent a more realistic lane-change trade-off. The results show that the lane-change initiation model obtained by this method can reproduce the personal lane-change tactic, and the performance of the customized models (average accuracy 86.1%) is much better than that of the non-customized models (average accuracy 75.7%). This method allows continuous improvement of customization for users during fully autonomous driving even without human-driving experience, which will significantly enhance the user acceptance of high-level autonomy of self-driving vehicles.

Keywords: Intelligent transportation systems, Smart urban Environments, Decision Support Systems
Abstract: Among all the transportation systems that people use, the public traffic-ways are most common and dangerous resulting in a significant number of fatalities per day worldwide. Statistics have shown that the mortality rates related to traffic accidents are more among youth. Although various road safety strategies and rules are developed by the government and law-enforcement agencies to combat the situation, these methods mainly target the design, operation, and usability of traffic-ways. Most of the recent data-driven analysis papers model the traffic patterns or predict accidents from the past data. In this paper, we consider a comprehensive, year-long fatality analysis reporting system (FARS) data to analyze the role of various factors related to humans, weather and physical conditions (e.g., road surface, light condition, etc.) involved in traffic accidents. We build an intelligent risk prediction model that can help decision-makers to ensure road safety. The proposed model estimates (i.) the accident risk over a future time frame, and (ii.) the risk associated with the drivers present on the traffic-way based on the driver's behavior, history, environmental conditions, and physical conditions related to traffic-way.

Keywords: Conflict Resolution, Decision Support Systems, Homeland Security
Abstract: In game theory and other decision-making frameworks that seek solutions in conflict situations, the ranking that ordinally expresses degrees of the decision maker's preference for possible strategies has a significant impact on the analysis results. In this paper, we examine a new method to formulate preference rankings with the perspective of avoiding escalation of conflicts that incorporates TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution). The Graph Model for Conflict Resolution (GMCR) was used for the analysis, using the preference ranks obtained by both the standard method in which the analysts set the preference ranks subjectively and the new TOPSIS method, which incorporates a de-escalation perspective. As a result, it was found that the analysis method using TOPSIS ranking with de-escalation aspect was able to obtain conflict analysis results that more clearly reflected the intention of the analysis when compared with the standard method.

This paper aims to propose a method of formulating preference order of a decision-maker for conflict resolution from the aspect of de-escalation of conflict. We conducted a stability analysis in the framework of GMCR using preference orders obtained by the conventional method as well as by a TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) method modified for de-escalation(TOPSIS-DES). Based on the analysis results, we found that the method using preference order by TOPSIS-DES was able to obtain results that more clearly reflected the aspect of the analysis, compared to the results obtained by the conventional approach.

Keywords: Conflict Resolution, Cooperative Systems
Abstract: The evolution of cooperation can be investigated using Prisoners’ Dilemma (PD) game models on spatial networks. It has been shown that other-regarding preferences, such as inequality aversion, a taste for fairness, or reciprocal preference, can cause cooperative behavior to evolve. In this paper, we consider whether relationships among agents, alone or in combination with other-regarding preference, can drive cooperation. We study the emergence of cooperation in PD games on a two-dimensional spatial network where some individuals are reciprocators, altering their future behavior based on comparison with a randomly chosen neighbor. Simulation results show that, if the intensity of reciprocal preference is fixed, the frequency of cooperation increases with the fraction of reciprocators. When reciprocal preference intensity is high, a low level of cooperation can be sustained, even if there are few reciprocators -- though cooperation does not diffuse through the population. We also show that the particular linking rule matters, in that cooperators are more likely to survive under a Cooperate-Stay, Defect-Shift (CSDS) linking rule, as opposed to a Win-Stay, Lose-Shift (WSLS) rule. As the fraction of reciprocators increases, the CSDS rule provides a more favorable environment for the evolution of cooperation. In addition, there is a threshold fraction of reciprocators such that a large value of network evolution strength contributes to cooperation most the threshold is exceeded. On the other side of the threshold, stronger reciprocal preference intensity does not necessarily promote cooperation more powerfully. Our results provide insight into how relations between neighbors can be a potent force, in combination with reciprocal preference, in inducing cooperation.

Keywords: Conflict Resolution, Decision Support Systems, Intelligent Assistants and Advisory Systems
Abstract: In recent years, Japan is experiencing a drastic increase of inbound tourists. In order to improve the environment for accepting foreign tourists visiting Japan, the Licensed Guide Interpreters Act was partially revised in 2018, which allows anyone to work as a compensated guide interpreter without the national license. Because inbound tourists have a wide variety of preferences on sightseeing, guides are needed to manage those diversified or sometimes complex requests flexibly. Thus, it is an important issue to ensure a quality of the interpreted guide services, as such uncertified guides may include inexperienced volunteers. This paper proposes a decision support system for inexperienced guides who is developing sightseeing plans for foreign visitors. First, inbound tourist behavior patterns in a city in Japan are extracted from a guide log data, which are recorded by some volunteer guides. By applying the collaborative filtering, the support system is constructed that predict and recommend sightseeing spots and activities by inputting new visitors' interested spots and/or activities. Experimental test demonstrates that the proposed system holds a certain level of accuracy.

Keywords: Conflict Resolution, Decision Support Systems
Abstract: Labor strikes are an example of conflict which may prove difficult to resolve and may have high impacts on society and organizations. The antagonistic nature of each party’s preferences highlights the complexity of reaching an agreement. This paper discusses how the strike problem which has already been structured in the literature within a games theory perspective may be approached using the Graph Model for Conflict Resolution (GMRC) approach. The advantages of using this approach derive from the conclusions that could be drawn without having precise information about each party’s preferences.

Keywords: Model-based Systems Engineering, System of Systems, Systems Medicine
Abstract: The outbreak of public health emergencies not only threatens people's life safety, but also has a series of secondary effects. In this paper, based on SEIR classical infectious disease model, covid-19 epidemic model is constructed by using system dynamics method.Based on different isolation measures and protection measures in different regions, the model was simulated to dynamically describe the change rule of epidemic infection number with time. The results show that the earlier the government takes isolation measures, the more active people will protect themselves, which can effectively reduce the number of infected people and control the epidemic situation faster.

Keywords: Brain-based Information Communications, Assistive Technology
Abstract: Functional near-infrared spectroscopy (fNIRS) is an emerging optical technology that can be used to monitor brain function at the bedside. Recently, there has been a great interest in using fNIRS as a tool to assess command-driven brain activity in patients with severe brain injuries to infer residual awareness. In this study, time-resolved (TR) fNIRS, a variant of fNIRS with enhanced sensitivity to the brain, was used to assess brain function in patients with prolonged disorders of consciousness (DOC). A portable system was developed in-house, and patients were assessed in their homes or long-term care facilities across London and the Greater Toronto Area, Canada. Five DOC patients and one locked-in patient were recruited in this study, and motor imagery was used to elicit command-driven brain activity. TR-fNIRS data were analyzed using the general linear modelling (GLM) approach, as well as with basic machine learning. Three patients showed activity with GLM, four with machine learning, and two with both techniques. Interestingly, the two patients that showed activity by both approaches also had detectable motor imagery activity by functional magnetic resonance imaging. These promising preliminary results highlight the potential of TR fNIRS as a tool to probe consciousness and map brain activity at the bedside.

Keywords: Human-Machine Interface, Brain-based Information Communications, Human-Machine Cooperation and Systems
Abstract: In this publication we present a novel P300 speller that could be used for communication with patients with disorders of consciousness. The stimulation for the P300 is done tactilely on seven different body locations. Tests on four healthy users were done and resulted in an average accuracy of 95% when answering a simple “yes” versus “no” questions. We further implemented a statistical test, that additionally provided a so-called zero-class. If the classification result “yes” or “no” is uncertain, and therefore may be wrong, the speller provides the so-called zero-class as output. The answer is therefore considered ambiguous. After adding the zero-class calculations to the analysis of the same data set, the percentage of correct answers decreased from 95% to 87.5%, however, it has a big advantage of no single wrong classification.

Keywords: Human-Machine Interface, Human-Computer Interaction
Abstract: The assessment of consciousness and unconsciousness is a challenging issue in modern neuroscience. Consciousness is closely related to memory consolidation in that memory is a critical component of conscious experience. So far, many studies have been reported on memory consolidation during consciousness, but there is little research on memory consolidation during unconsciousness. Therefore, we aim to assess the unconsciousness in terms of memory consolidation using electroencephalogram signals. In particular, we used unconscious state during the nap; because sleep is the only state in which consciousness disappears under normal physiological conditions. Seven participants performed two memory tasks (word-pairs and visuo-spatial) before and after the nap to assess the memory consolidation during unconsciousness. As a result, spindle power in central, parietal, occipital regions during unconsciousness was positively correlated with the difference in location memory performance. With the difference in memory performance, there was also a negative correlation between delta connectivity and word-pairs memory, alpha connectivity and location memory, and spindle connectivity and word-pairs memory. Additionally, brain activity and connectivity for differences according to nap and unconsciousness during memory recall were explored. These findings could help present new insights into the assessment of unconsciousness by exploring the relationship with memory consolidation.

Keywords: Human-Machine Interface, Augmented Cognition, Assistive Technology
Abstract: Brain-computer interfaces (BCIs) have shown enormous promise in the detection of consciousness in minimally responsive individuals. To date, most BCIs have relied on the presence of high-level cognitive abilities (e.g. attention, language comprehension) in non-responsive individuals, resulting in a large number of cases of undetected – or covert – consciousness. An alternate approach is to measure the underlying properties of brain networks, which makes no assumptions about the presence of certain cognitive capacities. Brain networks can be represented through functional connectivity of different brain areas. To date, the vast majority of studies have used time-averaged functional connectivity to represent a state of consciousness. In this paper, we compare time-averaged versus time-resolved functional connectivity, and the information contained by each in different states of consciousness. We present a novel analysis to evaluate the dynamic properties of time-resolved, high-resolution estimates of phase-based functional connectivity using weighted phase lag index (wPLI) calculated from high-density EEG. In a case study of two individuals in disorders of consciousness, we demonstrate that time-resolved functional connectivity reflects the dynamic properties of brain networks, providing more information about an individual’s state of consciousness than traditional time-averaged approaches. Our findings support timeresolved functional connectivity as the basis for a passive BCI with the potential to characterize the level of consciousness in behaviourally unresponsive patients.

Keywords: Human-Machine Interface, Mental Models
Abstract: Patients in intensive care for severe acute brain injury will undergo a series of behavioural and neurological assessments to evaluate their residual neural function and track the progression of their recovery. However, the degree to which covert conscious awareness is retained during the acute stages of a serious brain injury is unclear. In this study, we developed an EEG protocol to assess narrative processing—a proxy measure of awareness—during English and French versions of a naturalistic listening task. In two groups of healthy controls, we used EEG and a correlated components analysis to uncover a common pattern of neural activity associated with following the plot of a short, suspenseful audio clip from the movie “Taken”. Inter-subject neural correlations (ISCs) were used to compare the similarity of the EEG between participants during intact and scrambled versions of the audio. We found that the intact English version of “Taken” produced significantly higher ISCs than the scrambled version, though we did not observe a similar effect for the French audio. However, both the intact English and French versions of “Taken” produced significantly more time windows of ISCs across the group than their respective scrambled versions. Finally, the time course of ISCs for the intact English audio was significantly correlated with an independent set of subjective ratings of suspense during the task, while the correlation between suspense and the time course of ISCs for the intact French audio approached significance. These preliminary results suggest that our naturalistic listening protocol could be used to assess narrative processing, and thus, preserved awareness at the bedside using EEG in patients with acute brain injury in critical care centres across Canada.

Keywords: Biometric Systems and Bioinformatics, Computational Intelligence, Computational Life Science
Abstract: The paper proposes to employ deep convolutional neural networks (CNNs) to classify noncoding RNA (ncRNA) sequences. To this end, we first propose an efficient approach to convert the RNA sequences into images characterizing their base-pairing probability. As a result, classifying RNA sequences is converted to an image classification problem that can be efficiently solved by available CNN-based classification models. The paper also considers the folding potential of the ncRNAs in addition to their primary sequence. Based on the proposed approach, a benchmark image classification dataset is generated from the RFAM database of ncRNA sequences. In addition, three classical CNN models have been implemented and compared to demonstrate the superior performance and efficiency of the proposed approach. Extensive experimental results show the great potential of using deep learning approaches for RNA classification.

Keywords: Biometric Systems and Bioinformatics, Machine Learning
Abstract: The dynamic tumor tracking radiotherapy (DTT-RT) is the cutting-edge technology that attempts to track and irradiates the moving tumor continuously. Prediction of the 50 - 500 ms future position of the tumor is necessary for successful implementation of DTT-RT to compensate for the positioning lag of the multi-leaf collimator (MLC). It is known that lung tumor exhibits respiratory induced motion. Precise prediction of lung tumor motion is known to be a very difficult problem since it exhibits large variation both on the amplitude and the phase of the trajectory, although it is induced by respiration of a patient that is nearly periodic. This paper proposes a prediction model of a lung tumor motion. The proposed model utilizes the high-order repetitive control to generate prediction corresponding to periodic baseline of the trajectory and the long-short term memory to cope with the remaining portion. We have developed nine personalized prediction models for nine patients who underwent respiratory gated stereotactic body radiotherapy in Yamaguchi University Hospital to predict 666 ms ahead 3D tumor position for each patient. The average 3D RMS position error for the nine patients was 2.18 mm (+/-1.66).

Keywords: Biometric Systems and Bioinformatics, Machine Learning, Neural Networks and their Applications
Abstract: Emergency Department (ED) crowding has become an issue of delayed patient treatment and even a public healthcare problem around the world. According to recent research studies of many countries, the increasing number of patients in the emergency department which has led to unprecedented crowding and delays in care. For that reason, triage into five-level Emergency Severity Index (ESI) has become a major method for improving medical priorities in ED. Although the ESI mitigates the process of ED treatment, so far it still heavily relies on the nurse's subjective judgment and is easy to triage most patients to ESI level 3 in current practice. Therefore, a system that can help the doctors to accurately triage a patient's condition is imperative. In this work, we propose a system based on the patients’ ED electronic health record to predict hospitalizations after assigned procedures in ED are completed. While most of the related studies have employed traditional machine learning for triage-related classification and highly relied on a feature selection process, our proposed system used data-to-image transform to produce the input and a convolutional neural network as a classifier. For validation, the data from an open dataset (National Hospital Ambulatory Medical Care Survey) is used which includes 118,602 patient visits of United States EDs from 2012 to 2016 survey years. To sum up, the resulting AUROC and the accuracy achieve 0.86 and 0.77, respectively, in our work.

Keywords: Biometric Systems and Bioinformatics, Neural Networks and their Applications, Cybernetics for Informatics
Abstract: Rheumatoid arthritis (RA) patients have osteoarticular deformation in the early stage, and suffer worse from joint deformity and even loss of function in the later stage. Accurate evaluation of the patient’s physical condition is of importance as it would significantly help to decide appropriate care, medications or medical interventions needed. Thus, a fast and efficient risk factor selection algorithm demonstrates a clinical significance for the more precise diagnosis, and an accurate prediction model will hopefully be able to improve current treatment. In this paper, we designed a novel and universal architecture, broad learning attribute selection system (BLAS), to deal with the risk factor diagnosis and disease performance prediction on RA patients. The attribute selection based on rough set and entropy can identify significant risk factors affecting RA and broad learning possesses the ability of randomly generating nodes to investigate the desired connection weights simultaneously without the need for deep architecture. Experiments on clinical RA patients’ dataset demonstrated that our proposed BLAS model achieved the highest average accuracy of 99.67% with mean absolute error of 0.32%, compared with the state-of-the-art methods. The results proved the robust classification ability of BLAS in RA risk factors assessment and prediction.

Keywords: Evolutionary Computation, Agent-Based Modeling, Computational Intelligence
Abstract: When some resources are to be distributed among a set of agents following egalitarian social welfare, the goal is to maximize the utility of the agent whose utility turns out to be minimal. In this context, agents can have an incentive to lie about their actual preferences, so that more valuable resources are assigned to them. In this paper we analyze this situation, and we present a practical study where genetic algorithms are used to assess the benefits of lying under different situations.

Keywords: Evolutionary Computation, Computational Intelligence, Machine Learning
Abstract: Feature selection is a technique used to reduce an original set of features to a subset containing the most salient features. Reducing the feature set to the most significant subset of features typically results in an increase in the overall accuracy of a system. It has been shown that in some cases, the use of feature selection can make an underlying system susceptible to adversarial attacks. In this paper, we investigate the susceptibility of a feature selection-based Authorship Attribution System (AAS) to adversarial authorship attacks. The AAS studied is an instance of a Linear Support Vector Machine (LSVM). The feature selection algorithm used is an instance of Genetic & Evolutionary Feature Selection (GEFeS). In order to evaluate the GEFeS+LSVM-based AAS, we use three adversarial authorship masking techniques to generate adversarial texts to attack the AAS. Our results show that in some cases the GEFeS+LSVM-based AAS is more susceptible to adversarial authorship attacks. We provide a simple measurement to determine whether the use of GEFeS is beneficial or detrimental to a LSVM-based AAS.

Keywords: Evolutionary Computation, Computational Intelligence, Optimization
Abstract: Surrogated assisted evolutionary algorithms are commonly used to solve real-world expensive optimization problems. However, in some situations, no online data is available during the evolution process. In this situation, we have to build surrogate models based on offline historical data, which is known as offline data-driven optimization. Since no new data can be used to improve the surrogate models, offline data-driven optimization remains a challenging problem. In this paper, we propose a Gaussian process assisted offline estimation of multivariate Gaussian distribution algorithm to address the offline data-driven optimization problem. Instead of using surrogate models to predict the fitness values of individuals, we utilize a surrogate model to predict the rankings of individuals based on the frequently used lower confidence bound. In this way, the robustness of the proposed algorithm could be enhanced. Experiments are conducted on five commonly used benchmark problems. The experimental results demonstrate that the proposed offline surrogate model and the multivariate Gaussian estimation of distribution algorithm are able to achieve competitive performance.

Keywords: Evolutionary Computation, Heuristic Algorithms, Optimization
Abstract: We propose a chaotic evolution algorithm with elite strategy. The conventional chaotic evolution algorithm uses each individual to search in its local area. The proposed algorithm searches the parameter space always around the elite individual from the last generation. We evaluate the proposed algorithm in both single-objective and multi-objective optimization problems. In the single objective optimization problem, the elite is the individual has the best fitness value, and in the multi-objective optimization problem, the elites are the individuals in the first Pareto front. We design and evaluate these two algorithms with elite strategy using single- and multi-objective benchmark functions. We design a jump strategy to avoid searching within a local optima areas by applying elite strategy several generations one time. The numerical evaluation results demonstrate the proposed algorithm has strong local exploitation capability in the early generations. The optimization performance of chaotic evolution algorithm has a potential possibility to apply in high dimensional and more complex optimization problems.

Keywords: Evolutionary Computation, Machine Learning
Abstract: Evaluation metrics play an important role in accessing the performance of a regression method. In practice, these multiple evaluation metrics can be used in two ways. The first way defines a loss function by aggregating multiple metrics, while the second way defines a multiobjective loss function by considering each metric as an objective function. In this paper, we propose a new way to use multiple evaluation metrics, which is different from the aggregating method and the mutliobjective method. Our method is based on genetic programming. The idea is to randomly use one metric in each iteration of the selection operator. Therefore, multiple metrics can be used alternatively in the running process. To validate the effectiveness of our new approach, we conduct experiments on ten benchmark datasets. The experimental results show that the new approach can improve the population diversity, and can achieve the performance better than or similar to that of the traditional symbolic regression algorithms.

Keywords: Fuzzy Systems and their applications
Abstract: For the multiple criteria decision problem in the fuzzy environment of Pythagorean theorem, the existing set operators seldom consider the relation between criterions, and choose optimal alternative only through a single measure when the alternatives are sorted. In order to solve the problems, the Bonferroni operator is extended to the Pythagorean fuzzy set (PFS) to provide the Pythagorean fuzzy Bonferroni method, and the alternatives is ranked by the synthetic measure. In this paper, firstly, triangular fuzzy numbers(TFNs) are used to represent parameter values, and then the Pythagorean triangular fuzzy interaction geometric Bonferroni mean(PTFIGBM) operator and the Pythagorean triangular fuzzy interaction weighted geometric Bonferroni mean (PTFIWGBM) operator of Pythagorean TFNs environment are proposed. Some special cases of the proposed new aggregation operators are studied. A multi-criteria decision making method based on PTFIGBM operator and PTFIWGBM operator is developed. The distance measure in the Pythagorean TFNs environment is innovatively proposed in this paper, and the score function and the distance measure are aggregated into a comprehensive measure to sort the alternatives. Finally, a numerical example is given to illustrate the new method, and some parameters are analyzed and compared with other methods to further demonstrate the advantages of the proposed new method.

Keywords: Fuzzy Systems and their applications, Information Assurance & Intelligent, Agent-Based Modeling
Abstract: Abstract—In a resource allocation system, resource suppliers and customers can be naturally modelled as autonomous and interactive entities. In this context, we propose in this paper a multiagent system architecture based on trust and honesty concepts between agents in order to synchronize resource allocation in a distributed environment. Indeed, agents use several means in order to allocate resources efficiently as dialogue, adaptability, cooperation, collaboration and even negotiation in addition to the notion of trust. So, individual agents have to evaluate the trustworthiness of others to select those to interact with. Moreover, resource inadequacies can exist in the resource allocation systems, and it is difficult to meet the resource requirements of all agents simultaneously. To overcome these difficulties, we propose a distributed multiagent resource allocation system that emphasizes the issues of agents trust and resource inadequacies, which is called MARA-T&R. In this system, the evidence theory is improved thanks to the Deng entropy to estimate the trustworthiness of agents. Additionally, we use the concept of reservations to solve the problem of resource inadequacies. Our simulation results highlight the excellent performances of this improved trust model and the efficiency of the proposed MARA-T&R system for resource allocation.

Keywords: Fuzzy Systems and their applications, Machine Learning
Abstract: The Choquet Integral (ChI) is an aggregation operator defined with respect to a Fuzzy Measure (FM). The FM of a ChI encodes the worth of all subsets of the sources of information that are being aggregated. The monotonicity and the boundary conditions of the FM have limited its applicability to decision-level fusion. In a recent work, we removed the boundary and monotonicity constraints of the FM to propose a Choquet Integral-based regression approach (CIR) that enables capacity beyond previously proposed ChI regression methods. In the same work, we also presented a quadratic programming (QP)-based method (batch-CIR) to learn the FM parameters of the ChI regression using the training data. However, the QP used for learning the FM scales exponentially with the dimensionality of the training data and thus it becomes impractical on data sets with 7 or more dimensions. In this paper we propose an iterative gradient descent approach, online CIR, to learn the FM. This method iteratively processes the training data, one data point at a time, and therefore requires significantly less computation and space at any time during the training. The application of the batch-CIR method required the dimensionality reduction of high-dimensional data sets to enable computation in a reasonable time. Our online-CIR approach has enabled us to extend the CIR regression approach to data sets with larger dimensionality. In our experimental evaluation using benchmark regression datasets, the online-CIR has outperformed the batch method on high-dimensional data sets while also matching the performance with batch-CIR on low-dimensional data sets.

Keywords: Fuzzy Systems and their applications, Machine Learning, Fuzzy Systems and Evolutionary Computing
Abstract: Fuzzy decision trees have been successfully applied in numerous domains. The popularity of these models comes notably from their interpretability, namely the ability of humans to understand them. However, on the contrary to neural networks, the induction of such models does not include a generation of their own feature space. In this work, the embedding of feature construction in fuzzy decision tree induction algorithms is studied, so that they can create new input features, without affecting the overall interpretability of the model. This method is successfully applied to a classification problem in high-energy physics to study the benefits of having constructed features in fuzzy decision tree on the classification scores, allowing them to have their own interpretable representation of the data.

Keywords: Machine Learning
Abstract: The careless of the driver gives rise to traffic accidents in automobiles. The inattention is made by the depletion of the driver’s attentional capacities, and the increase in the driver’s mental workload causes it. Therefore, it is important to evaluate the mental workload (MWL) of the driver in driving. The proposed method is used to map multidimensional biological signals into a stochastic space based on a mixed normal distribution model. The load state of the driver is evaluated, and the cognitive load can be determined from a posteriori probability. In the experiments reported here, tasks performed to examine tracking of the vehicle in front and N-Back evaluation helped to clarify the cognitive load of the subjects, for whom multidimensional biosignal monitoring was performed. The results demonstrated a high correlation between evaluation and NASA-TLX values. In the other experiments, the increase in evaluation values was confirmed while operating the satnav system. Thus, it is presented that the proposed method can estimate the driver’s MWL in real time.

Keywords: Machine Learning
Abstract: How to achieve efficient cooperation among agents in partially observed environments remains an overarching problem in multi-agent reinforcement learning (MARL). Value function factorization learning is a promising way as it can efficiently address multi-agent credit assignment problem. However, existing value function factorization methods have been focusing on learning fully decentralized value functions, which are not effective for some complex tasks. To address this limitation, we propose a framework which enhances value function factorization by allowing communication during execution. Communication introduces extra information to help agents understand the complex environment and learn sophisticated factorization. Furthermore, the proposed mechanism of communication differs from existing methods since we additionally design a descriptive key along with the message. By the descriptive key, agents can dynamically measure the importance of different messages and achieve attentional communication. We evaluate our framework on a challenging set of StarCraft II micromanagement tasks, and show that it significantly outperforms existing value function factorization methods.

Keywords: Machine Learning
Abstract: Supervised learning technologies represented by neural networks have made great progress in many fields. In particular applications such as image recognition and natural language processing, the entire computing process is completely handed over to the machine learning algorithm to directly learn the mapping from the feature space to the expected output, without considering much of the semantical information and domain knowledge of the data. In this paper, we propose a generic data refinement approach called divideup, which incorporates finer semantical information into the dataset to obtain a prediction model capturing more detailed information in the training data. By providing the information theory, we have high confidence that the learned model trained with the refined dataset has better prediction accuracy than the original one. We conduct extensive experiments on different datasets with the state-of-the-art neural network architectures such as ResNet and DenseNet. The experimental results show that divideup improves the prediction accuracy of all these deep learning architectures on the original test set. The divideup approach is also applied to other machine learning models such as random forest, XGboost and SVM. The results supports the conclusion that the refined training data obtained by divideup produces better prediction accuracy of the learned model.

Keywords: Machine Learning, Computational Intelligence, Fuzzy Systems and their applications
Abstract: This paper presents a machine-learning algorithm applied to a quadcopter application. We are proposing a fuzzy actor-critic learning (FACL) algorithm. This method enables a pursuer quadcopter to capture an evader quadcopter in the pursuit-evasion (PE) differential game. In this application, the pursuer learns its control strategies by interacting with evader and learning from past experiences. Both the critique and the actor are fuzzy inference systems (FIS). It is assumed that the pursuer knows only the instantaneous position and speed of the evader and vice versa. The FACL will generate the desired trajectory as the input for low-level controllers. Simulation results are presented for the PE differential game to demonstrate the practicality of our machine-learning algorithm.

Keywords: Neural Networks and their Applications
Abstract: Semantic segmentation is a critical method in the field of autonomous driving. When performing semantic image segmentation, a wider field of view (FoV) helps to obtain more information about the surrounding environment, making automatic driving safer and more reliable, which could be offered by fisheye cameras. However, large public fisheye datasets are not available, and the fisheye images captured by the fisheye camera with large FoV comes with large distortion, so commonly-used semantic segmentation model cannot be directly utilized. In this paper, a seven degrees of freedom (DoF) augmentation method is proposed to transform rectilinear image to fisheye image in a more comprehensive way. In the training process, rectilinear images are transformed into fisheye images in seven DoF, which simulates the fisheye images taken by cameras of different positions, orientations and focal lengths. The result shows that training with the seven-DoF augmentation can improve the model’s accuracy and robustness against different distorted fisheye data. This seven-DoF augmentation provides a universal semantic segmentation solution for fisheye cameras in different autonomous driving applications. Also, we provide specific parameter settings of the augmentation for autonomous driving. At last, we tested our universal semantic segmentation model on real fisheye images and obtained satisfactory results. The code and configurations are released at https://github.com/Yaozhuwa/FisheyeSeg.

Keywords: Neural Networks and their Applications
Abstract: This paper focuses on studying the H∞ performance state estimation problem for static neural networks (SNNs) with time-varying delays. Consider the estimation problem for delayed SNNs, the previously well-known Lyapunov-Krasovski functional (LKF) methods are devoted to constructing more and more complex functionals, in which each term is positive definite function. Hence it is difficult to solve and optimize in designing estimators. In this paper, the simple delay- product-type LKF with negative definite terms is established for the use of the Wirtinger based inequality together with mixed convex combination approach. The delay dependent conditions in terms of linear matrix inequalities (LMIs) are obtained which lead to less conservative and more flexible estimator design results. Finally, a numerical example is given to demonstrate the merits over the existing ones.

Keywords: Neural Networks and their Applications, Biometric Systems and Bioinformatics, Machine Learning
Abstract: Nuclear cataract is one of the most common types of cataract. In the recent, ophthalmologists are increasingly using anterior segment optical coherence tomography (AS- OCT) images to diagnose many ocular diseases including cataract. The relationship between cataract and the lens opacity based on AS-OCT images has been being studied in clinical pioneer research. However, using AS-OCT images to classify cataract automatically based on computer-aided diagnosis (CAD) technique has not been seriously studied. This paper proposes a novel Convolutional Neural Network (CNN) model named GraNet for nuclear cataract classification based on AS-OCT images. In the GraNet, we introduce a grading block to learn high-level feature representations based on the pointwise convolution method. To further improve the classification performance, we propose a simple and efficient cross-training method is comprised of focal loss and cross- entropy loss. Extensive experiments are conducted on the AS- OCT image dataset, the results demonstrate that the proposed methods achieve better nuclear cataract classification results than baselines

Keywords: Neural Networks and their Applications, Computational Intelligence, Expert and Knowledge-based Systems
Abstract: The present neuromarketing study aims to predict how consumers evaluate brand extension from their brain activity. Brand extension refers to the use of well-established brand name to new goods or service. In our experiment, participants evaluated whether a given brand extension sample was acceptable during functional magnetic resonance imaging (fMRI) scanning. Brand extension samples included parent beverage brand name and extended goods name from beverage or household appliance categories. We pre-processed 3-D fMRI image data and extracted 2-D feature images based on a preliminary study. To overcome the limited number of fMRI samples, we conducted image augmentation for the training dataset. A deep neural network model with the convolutional neural network (CNN) architecture was used to classify fMRI images in response to visual presentation of each brand extension sample into one of the two classes: acceptable vs. non-acceptable. The train classifier was tested using 10-fold cross validation. Our model estimated the evaluation of brand extension with high accuracy (90.4%). This result indicates that one can predict how a consumer evaluates a new brand extension proposal only by their brain activity.

Keywords: Neural Networks and their Applications, Computational Intelligence, Machine Learning
Abstract: With the emergence use of social media, millions of micro-messages are exchanged daily. Although micro-messages are a powerful and efficient way to communicate among individuals, their anonymity and short-length characteristics give rise to a real challenge for Author Identification studies. In this paper, we tackled the Author Identification of micro-messages problem via Convolutional Neural Networks (CNNs). Specifically, we introduce a novel Multi-Channel CNN architecture that processes different features of text via word and character embedding layers, and utilizes both pre-trained word embedding and character bigram embeddings. We examine the usefulness of different feature types and show that the combination of embedding layers can capture different stylometric features. We conduct extensive experiments with a varying number of authors and writing samples per author. Our results show that our proposed method outperforms the state-of-the-art system on a Twitter dataset that contains 1,000 authors.

Keywords: Cybernetics for Informatics, Computational Intelligence, Optimization
Abstract: Abstract—There is a growing concern in recycling plants for minimizing the negative environmental impacts (such as carbon emissions) of disassembling end-of-life products. Uncertainty such as their internal structural changes exists when disassembling them. In this paper, we propose a stochastic multi-objective disassembly sequencing and line balancing problem based on an AND/OR graph. By considering disassembly failure risk, we construct objectives of maximizing profit and minimizing carbon emission and energy consumption. Then, a novel multi-objective discrete grey wolf optimizer is proposed to solve it. A hammer drill case is given to show its effectiveness and feasibility. The experimental results show the superiority of the proposed algorithm over classical non-dominated sorting genetic algorithm II and multi-objective evolutionary algorithm based on decomposition.

Keywords: Image Processing/Pattern Recognition, Machine Vision, Machine Learning
Abstract: Reliable detection of obstacles around the vehicle is crucial for autonomous cars. We present a novel and robust ground shape invariant feature method for general obstacle detection with a car-mounted monocular fisheye camera. Both stationary and moving obstacles can be detected by our approach without recovering the camera motion. Firstly, In order to compute the ground shape invariant feature, the image is mapped into the top view image. And then feature points are extracted and matched between adjacent frames. Secondly, the points are grouped according to image patch partition. Finally, the ground shape invariant feature is computed for each group of points to detect obstacle points. Extensive experiments have been carried out with prerecorded video sequences including various obstacle types, various scenes and various illumination conditions. The experimental results show promising detection performance of the proposed method.

Keywords: Optimization, Cybernetics for Informatics, Intelligent Internet Systems
Abstract: In order to better meet the needs of the green industrial Internet of things, this paper studies the anchoring psychology of online consumers and proposes a pricing model that considers online consumers to be anchored by the product price. In this model, the cognitive bias of online consumers affected by anchoring effect is described in a utility function by using the anchoring-adjustment heuristic, and the consumer choice behavior and online product pricing strategy are studied with a Multinomial Logit Model (MNL). We study the effect of price anchoring point and anchoring degree on optimal pricing. In particular, when the cost is greater than the price anchoring point, the greater the anchoring degree is, the smaller the profit will be. This paper provides a more flexible pricing mechanism for enterprises based on historical consumption data through customer behavior analysis, and it will accelerate the construction of the green industrial Internet of things.

Keywords: Heuristic Algorithms, Cybernetics for Informatics, Computational Intelligence
Abstract: A Disassembly Line Balancing Problem (DLBP) exists in the remanufacturing of discarded products. It involves such factors as sequence-dependent among components, multi-resource constraints, limited number of workstations, uncertainty of disassembly time, and disassembly failure risk. Effective decisions can be made by taking them into full consideration. This work establishes a stochastic sequence-dependent multi-objective DLBP model subject to disassembly failure and resource constraints. Its objectives are maximization of profit and minimization of energy consumption. A multi-objective cuckoo search algorithm is proposed. Then, three real products are disassembled to verify the effectiveness and feasibility of the proposed approach. Experimental results show the superior of the proposed algorithm over multi-objective artificial bee colony algorithm and non-dominated sorting genetic Algorithm II.

Keywords: Cybernetics for Informatics, Computational Intelligence, Intelligent Internet Systems
Abstract: Mission-critical communication (MCC) enables and supports operations by providing reliable connectivity and interoperability, facilitating operational continuity and allows mission-performers to focus on mission goals and objectives. Any communication technology used in isolation may fail. For instance, land mobile radio (LMR) networks may provide poor coverage to tactical “push-to-talk” radio devices within stone buildings, while cellular devices may not satisfy strict performance criteria (e.g. setup and response time). An alternative approach would be dynamic orchestration of such hybrid communication networks, which also involve Bluetooth, cellular, and cloud-based networking technologies. We propose an integrated approach that accounts for situation, location, and connectivity considerations to enhance MCC network availability, and mission-performers’ connectivity and readiness, by harnessing communication, location, and situational awareness in networking technologies, applications, and users. This framework provides a holistic cyber-physical perspective on the problem. Our approach is useful in various real-life applications for operational connectivity of first responders, e.g. when breaking into a scene of an emergency, in which LMR coverage is expected to deteriorate significantly.

Keywords: Assistive Technology, Human Performance Modeling, Human Factors
Abstract: Stroke survivors often show a limited recovery in the hand function even after the recovery period (3-6 months after stroke) and at-home hand rehabilitation is common due to the long-term nature of hand rehabilitation and the limited medical resources. We designed a home-based hand rehabilitation training and compensation feedback system. A low-cost simple orthosis glove, a set of hand rehabilitation training games and a compensation detection and feedback module were designed and developed in this system. A preliminary test was carried out on the system and the results showed that the training section (the orthosis glove and the hand rehabilitation training games) of the system was friendly to the subjects and the subjects were more receptive to the system and the compensation detection and feedback module had a promising performance. This system can not only provide high intensity and incentive hand rehabilitation training, but also guide the stroke patients to correct wrong upper body postures during the training process, which can achieve better rehabilitation results. The system has the potential to become an effective home-based hand rehabilitation training and compensation feedback system.

Keywords: Assistive Technology, Human-Machine Cooperation and Systems
Abstract: Telerehabilitation with Robotic Exoskeletons is an emerging technology aimed at assisting to restore patients’ mobility using a master and slave robotic system. Some of the main challenges for achieving good tracking performance, stability and transparency in telerehabilitation are nonlinearities, uncertain and time-varying parameters in the robot and human models, and communication delays. Additionally, a paramount challenge for this technology is ensuring safe and compliant interaction between the robots and the human operators. This paper presents a novel control approach utilized during unilateral and bilateral teleoperation which address these challenges. An Adaptive Impedance Controller is designed using Lyapunov based methods for the master exoskeleton while a Proportional Derivative Impedance Controller is implemented on the slave exoskeleton. Subsequently, a torque limiter technique was implemented on the master side to ensure stability in the presence of time delays. The advantages of these controllers are that they address unknown dynamics, incorporate designed impedance response for rehabilitation applications, and are simple to implement. Simulations for two two-degree-of-freedom robotic exoskeletons are provided to demonstrate the effectiveness of these methods in both passive and assistive telerehabilitation modes, and with time delays.

Keywords: Assistive Technology, Virtual and Augmented Reality Systems, Human-Machine Interface
Abstract: Fractures and injuries can happen anytime to any person. However, there are body parts such as the upper limbs that have a high recurrence of lesions such as Carpal Tunnel Syndrome (CTS), Scaphoid fracture and Trigger Finger (TF) which are more prevalent in young adult populations. The purpose of this work is to develop an AI-VR-based hand rehabilitation system with a quantitative objective scale that aims to optimize the rehabilitation of the patients. The system analyses muscle (EMG) signals using an AI algorithm to classify different rehabilitation movements and provides visual feedback through a Virtual Reality (VR) environment. Moreover, a hand tracking system was used to acquire the difference in degrees for each movement to keep track of the hand movement in order to provide a better measure of accuracy.

Keywords: Assistive Technology, Wearable Computing, Companion Technologies
Abstract: The design and implementation of an integrated wearable face recognition and training system for prosopagnosia patients is presented. The purpose of this assistive technology is to provide real-time memory assistance and long-term rehabilitation. The real-time face recognition mode provides audio and visual notification of people who interact with the subject, while the at-home training mode combines features of mnemonic and perceptual training to help with prosopagnosia rehabilitation. In addition, a custom eye tracker is developed to determine the person who the subject is making eye contact with in a crowd. Using the inverted face effect to mimic the difficulties of prosopagnosia patients, clinically healthy participants have shown improvements in their face-naming abilities. Early results indicate the system's potential to enrich the well-being of prosopagnosia patients.

Keywords: Assistive Technology, Human Factors, Human-Machine Cooperation and Systems
Abstract: Most stroke patients with hemiplegia have difficulty on heel rocker function due to weak dorsiflexors at their paralyzed side. The proposed high-dorsiflexion assistive robotic technology (RT) supports ankle dorsiflexion during gait rehabilitation. Aside from the McKibben-type artificial muscle’s contraction to assist swing phase dorsiflexion, a tension spring is aligned in series to support heel rocker function upon heel strike. Because of different requirements of dorsiflexion torque during loading response phase, selection of suitable spring for corresponding user could be important. Springs with either excessively large or small coefficients might the normal heel rocker function. In this research, an identification method based on observing tension on the spring in loading response phase was derived. We aim for simple clinical setting and availability on patients with various pathological gait patterns, especially gait asymmetry. A case study on a stroke patient with hemiplegia was conducted to evaluate effect with the identified spring. Increase of knee angle (before intervention: mean 2.118°, SD 0.418°; during intervention: mean 12.814°, SD 1.764°) and shank angular velocity to the ground (before intervention: mean 117.300°/s, SD 9.491°/s; during intervention: mean 255.875°/s, SD 34.130°/s) indicates sufficient heel rocker function could be supported during intervention of the identified tension spring in this specific case.

Keywords: Human-Computer Interaction, Virtual and Augmented Reality Systems, Multi-User Interaction
Abstract: Hand gestures, whether static or dynamic, are a field of intense study and have several potential uses for humancomputer interaction in real-time systems. Static and dynamic hand gestures are rudimentary ways for human-computer interaction. This paper presents a technique for the text input method which is hand-gesture-recognition based. This compact handbased text input system is proposed for augmented reality (AR) and virtual reality (VR) devices. To recognize and classify hand gestures, the hand image is captured by a standard camera. After, the hand is segmented using background subtraction, and then the segmented hand gesture is input in the trained neural network for gesture recognition. Finally, hand movements are tracked and recorded using a convex hull algorithm. The corresponding written character is passed to a trained neural network. The proposed architecture is tested and the experimental results are compared with other methods, which showed that the proposed method performed better than traditional methods and achieved 96.12% accuracy, achieved accuracy is overall better than existing methods.

Keywords: Human-Machine Cooperation and Systems, Human-Machine Interface, Virtual and Augmented Reality Systems
Abstract: With the development of advanced communication technology, connected vehicles become increasingly popular in our transportation systems, which can conduct cooperative maneuvers with each other as well as road entities through vehicle-to-everything communication. A lot of research interests have been drawn to other building blocks of a connected vehicle system, such as communication, planning, and control. However, less research studies were focused on the human-machine cooperation and interface, namely how to visualize the guidance information to the driver as an advanced driver-assistance system (ADAS). In this study, we propose an augmented reality (AR)-based ADAS, which visualizes the guidance information calculated cooperatively by multiple connected vehicles. An unsignalized intersection scenario is adopted as the use case of this system, where the driver can drive the connected vehicle crossing the intersection under the AR guidance, without any full stop at the intersection. A simulation environment is built in the Unity game engine based on the road network of San Francisco, and human-in-the-loop (HITL) simulation is conducted to validate the effectiveness of our proposed system regarding travel time and energy consumption.

Keywords: Virtual and Augmented Reality Systems
Abstract: In the decision-making process, many complex problems may be difficult to deal with traditional approaches. In particular, in the construction sector, the large volume of information and the involvement of non-expert users can make time consuming and inconsistent the choice. In this paper, a new method supported by the Augmented Reality (AR) is proposed to simplify and improve the decision-making process. Such novel approach starts from the theoretical basis of the Analytic Hierarchy Process (AHP) and Simos-Roy-Figueira method (SRF) and develops a virtual environment to support the decision-making. In particular the AR provide a large amount of visual information transforming a complex decision method in a user-friendly tool. The proposed approach is applied in the field of building energy retrofitting in order to demonstrate its effectiveness. In particular, the goal of the analysis is the selection of the best panel, chosen from a set of experimental Precast Construction Panels, to improve the envelope performances of existing buildings. The decision involved both quantitative data (such as costs and thermal behavior) and qualitative data (such as the aesthetic impact).

Keywords: Virtual and Augmented Reality Systems, Interactive Design Science and Engineering, Human-Computer Interaction
Abstract: The internet-of-things (IoT) refers to the growing field of interconnected pervasive computing devices and the networking that supports smart, embedded applications. The IoT has multiple human-computer interaction challenges due to its many formats and interlinked components, and central to these is the need to provide sensory information and situational context pertaining to users in a more human-friendly, easily understandable format. This work addresses this by applying mixed reality toward expressing the underlying behaviors and states internal to IoT devices and IoT-enabled objects. It extends the authors’ previous research on IoT Avatars (mixed reality character representations of physical IoT devices), presenting a new head-mounted display framework and interconnection architecture. This contributes i) an exploration of mixed reality for smart spaces, ii) an approach toward expressive avatar behaviors using fuzzy inference, and iii) an early functional prototype of a hybrid physical and mixed reality IoT-enabled object. This approach is a step toward new information presentation, interaction, and engagement capabilities for smart devices and environments.

Keywords: Wearable Computing, Human-Machine Cooperation and Systems, Human-Computer Interaction
Abstract: Human motion tracking (HMT) has been a research focus in the last decades. In this paper, we propose an IMU/TOA-fusion-based platform to solve this problem. Firstly, Time-of-arrival (TOA)-based distance ranging method is considered to compensate for the drifting errors and accumulation introduced by inertial sensors. Secondly, a geometrical kinematic model and maximum correntropy criterion (MCC)-based Kalman filter method are proposed to fuse the multiple information. The open-source hardware and software are detailed in this paper for real-time human motion capture and reconstruction applications. Experiment results show that our proposed hardware can be easily equipped for total body motion reconstruction with a considerable enhancement of the wear-ability and comfort. Furthermore, the main achievements have been presented with a performance comparison between the proposed platform and state-of-the-art commercial ones. Above all, our proposed platform can significantly suppress the accumulative error and drifting problem of conventional inertial systems. More importantly, it realizes the open-source software and hardware, thus it has promising prospects for wearable human motion tracking applications.

Keywords: Human-Computer Interaction, Web Intelligence and Interaction, Interactive and Digital Media
Abstract: Over the past decade, online crowdsourcing has established itself as an emerging paradigm that industry and government have been using to harness the cognitive abilities of a multitude of users distributed around the world. In this context, microtask crowdsourcing has become the method of choice for addressing a wide range of diverse problems. Microtasks typically require a minimum of time and cognitive effort, but combined individual efforts have made it possible to accomplish great achievements. The goal of this paper is to contribute to the ongoing effort of understanding whether the same success that microtask crowdsourcing has achieved in other domains can be obtained in the field of social news curation. In particular, we ask whether it is possible to turn online news curation, typically a social and collaborative activity on the Web, into a model in which curatorial activities are mapped into microtasks to be performed by a crowd of online users.

Keywords: Human-Machine Cooperation and Systems, Human Factors
Abstract: With the increasing demand of personalized products and the application of emerging technologies, substantial unexpected events appears in smart factories. Machine learning based adaptive scheduling shows significant appeal in smart shop floors, yet still has limitations in accommodating unexpected events. This paper presents a novel framework of HCPS (Human Cyber Physical System) based on the conventional CPS. A human-machine cooperative mechanism is proposed to coordinate task allocation between human and machine. Meanwhile, in order to integrate human intelligence and machine intelligence within scheduling decision making, a novel human-machine cooperative approach for adaptive scheduling is put forward. In the process of online scheduling, human operators adjust the deviation of production indicators on the basis of current condition. Subsequently, an enhanced fuzzy inference system combining with human intelligence is designed to obtain optimal dispatching rules, in which parameters are reduced by a K-means algorithm and optimized by a PSO algorithm. Finally, a case study is performed on the Minifab model. The simulation results validate the superiority of the proposed framework and approaches, and show good potential in efficiency and stability.

Keywords: Human-Machine Cooperation and Systems, Information Systems for Design/Marketing
Abstract: Fog computing is an extension of cloud computing, which emphasizes distributed computing and provides computing services closer to the users. In this paper, we consider the biobjective task scheduling problem with heterogeneous resources in a fog-cloud computing system. The minimization of energy consumption and delay are the two objectives. We formulate a workload allocation problem model involving fog devices (FDs) and the cloud servers (CSs). The computing resources are heterogeneous on the energy consumption, processing capability and delay. An energy-aware greedy heuristic algorithm (EG) is developed to search for Pareto Front solutions. Experimental results show that the proposal is robust and effective for the problems under study.

Keywords: Human-Machine Cooperation and Systems, Team Performance and Training Systems
Abstract: Integrating various collaborative tools, a web-based Collaborative Working Environment can support collaborations between users. In collaborative processes, many resources are produced and stored distributively within these tools. This raises an issue: how to organize these resources in a Collaborative Working Environment. In our research, we intend to consider a Collaborative Working Environment as an ontology-based collaborative System of Information Systems and apply a collaboration context ontology for managing resources and generating resource recommendations to users. In this paper, we present a prototype of such environments and show how it can be used.

Keywords: Human-Machine Cooperation and Systems, Human-Computer Interaction, Human-Machine Interface
Abstract: In order to support a human in a human-machine system, the cooperating automation requires information about the goal pursued by the human. We model human-machine systems as a Partially Observable Markov Decision Process to develop an assistant system operating on maneuver or navigation level featuring an automatic detection of the human’s goal which is initially unknown to it. Predicting the next actions of the human allows for computing corresponding assistant actions by employing Partially Observable Monte-Carlo Planning With Observation Widening. These supporting actions are generated based on continuous action-, observation- and state spaces and are executed synchronously to the actions of the human. New information about the human’s goal is gathered through observations to further enhance future supporting actions. With a progressing certainty of the goal recognition, the assistant system is increasingly able to assist the human by completing the task both cooperatively or even fully autonomously, thus reducing workload, while always allowing for the human to smoothly in- or decrease their involvement. The assistant system demonstrates its ability to recognize the goal pursued by the human as well as to execute appropriate supporting actions while being robust to the human changing their goal in multiple experiments investigating the interaction of a real human with a simulated cooperative positioning scenario.

Keywords: Blockchain technologies
Abstract: Transformation of data into knowledge is the hallmark of modern medicine. As an evolving field of medicine, e-Health involves the electronic processing of a patient’s personal, medical and other health-related data to improve healthcare delivery. Data captured from clinical interactions between patients and their care providers, as well as health data collected through medical sensors, provide a rich source of data, known as patient medical records (PMRs), which can be processed in various ways to enhance the delivery of healthcare services. However, indiscriminate processing of PMRs could potentially result in the violation of the security or privacy of patients. To ensure that PMRs are not processed in ways that could be harmful to the security or privacy of the patients, modern data protection regulations, such as the European General Data Protection Regulation (GDPR), requires healthcare service provides to obtain the consent of a patient for any processing operation on their PMRs. The mechanism by which a patient exercises their right to control who can process their PMRs, when and for what purpose, is referred to as consent management in e-Health. Existing health information technology systems do not provide adequate support for consent management; there is a lack of transparency and auditability in the existing systems to monitor and ensure that healthcare service providers comply to the relevant data protection regulations in processing PMRs. The emerging blockchain technology offers an opportunity to design an e-Health consent management system that is compliant with modern data protection regulations such as GDPR. In this paper, we present the design and implementation of an e-Health consent management framework, based on the state-of-the-art blockchain technologies, for processing PMRs. Our analysis confirms that our system satisfies the requirements for consent management in e-Health

Keywords: AI in Financial Systems, Model-based Systems Engineering, Intelligent Assistants and Advisory Systems
Abstract: Credit scoring is a fast growing risk management methodology, where probability of default of customer borrowers are assessed by machine learning based on historical data. However, when the customer borrowers are in a different domain from the existing customers, the predictions are not executed properly because of domain adaptation problem. In this paper, we propose a transfer learning framework to predict probability of default extracting useful knowledge from an existing domain and divert it to a target domain by deriving latent feature vectors by Bayesian network structured learning. An experimental result showed the proposed method predicted the probability of default of customer borrowers more accurately than existing methods in a multi-domain space.

Keywords: AI in Financial Systems
Abstract: In this work, we will consider the dimension reduction of the set of time series, such as economic data, to find the meaningful basis vector for the set of data, and indicate which data use which basis vector. Usually each of the time series is analyzed independently in economics but here we will analyze the set of time series simultaneously. Since some of the economic data are measured as positive values and we want to decompose them as a mixture of the parts, we will apply non-negative matrix factorization to the economic data. Non-negative matrix factorization can compress dimensions by approximating a non-negative matrix with the product of two non-negative matrices. The two non-negative matrices are called the coefficient matrix and the basis matrix, and the basis matrix can be considered as a dimensionally compressed matrix. If the standard non-negative matrix factorization is used for economic data, the basis matrix may not be smooth. We think that the basis vectors should be smooth except a few special economical incidents. In the proposed method, a Graph-based non-negative matrix factorization is introduced to regularize the basis matrix of the time series. A path graph for representing the time series of economic data is incorporated into the non-negative matrix factorization as regularization. As a result, basis vectors that maintains the time series of economic data are decomposed. Furthermore, we propose to introduce a sparsity in the non-negative matrix factorization. Traditionally, the sparsity incorporated into non-negative matrix factorization has been used for basis vectors. However, the proposed method introduces the sparsity for coefficient vectors. Thus the proposed method, which simultaneously incorporates the sparsity for the coefficient vectors and the smoothness for the basis vectors, can extract the smooth basis vectors and the original economical data are approximated as the weighted sum of the few bases vectors. This allows us to discover economic trends and the best-fit trends for each data at the same time.

Keywords: AI in Financial Systems, Decision Support Systems
Abstract: The extremely high turnover of online advertising makes it one of the most important sources of income for many online ad publishers. Advertising through world wide web is mainly performed by Real Time Bidding in which the advertisers and the publishers participate to online auctions for trading the ad slots. Publishers usually set the reserve prices for their ad slots and any winning buyer in the auctions performed by ad exchanges has to pay at least the value of reserve price. Header bidding is a way of real time bidding and it becomes very popular, but how to use it together with advertising Exchanges (AdX) to achieve good revenue for online publishers is not well studied. In this paper, we propose a method that makes use of the historical auction data from header bidding and AdX to learn and optimize the reserve price for AdX. We propose a method based on supervised learning and survival analysis to increase the reserve price. The method assumes no information about current auctions and the bids of header bidding and AdX response are predicted and used to determine the highest possible reserve price. The experiments with real-world auction data show the promising results of our method in increasing the expected revenue of online publishers.

Keywords: Blockchain technologies
Abstract: The emergence of channel technology reduces the transaction verification time of blockchains. A channel with a stable state is helpful for completing transactions successfully. Under the assumption of node bounded rationality and replication dynamics of an evolutionary process, this paper presents a dynamic evolutionary game model based on node behaviors in blockchain channels. The model considers the cost of attack, attack success rate, defense, cooperation, and non-cooperation strategies during the game process. The defense strategy can help nodes resist different attacks. Nodes can dynamically adjust their own strategies according to different behaviors of attackers to achieve effective defense. The experimental results show that the proposed method is better than a lightning network channel in terms of transaction success ratio.

Keywords: Decision Support Systems
Abstract: Selecting non-ferrous scrap metal suppliers involves evaluating each supplier and its available scrap metals in terms of quantitative and qualitative criteria in each selection round. This paper presents a new approach for developing and selecting fuzzy multi-criteria decision making (MCDM) methods to address the non-ferrous scrap metal supplier selection problem with fuzzy data. The approach develops different fuzzy MCDM methods by combining three normalization processes and three aggregation processes commonly used in MCDM research. In particular, a specific defuzzification process is used to reflect the decision maker's risk attitude about the current global commodity market. A validation procedure using fuzzy c-means clustering is applied to select among inconsistent ranking results produced by different fuzzy MCDM methods. An empirical study on a non-ferrous scrap metal company in China is conducted to illustrate how fuzzy MCDM methods are developed and selected.

Keywords: Decision Support Systems, AI in Financial Systems
Abstract: Evolutionary algorithms or metaheuristic methods are common approaches applied in highly complex optimization problems, such as stock trading. In this paper we employ a novel approach for using a dynamic trading system with a technical indicator called the moving average (MA). Moreover, we utilize an improved metaheuristic algorithm, the global-best guided quantum-inspired tabu search algorithm (GQTS), which has a fast and stable feature to efficiently search for the optimal trading strategy of MA. Our approach employs the sliding window technique to avoid overfitting problem. In addition, we propose year-on-year sliding windows and 2-phase sliding window to adapt to the phenomenon of an economic cycle in the investment period and to efficiently solve stock trading problems. The experimental environment is the United States stock market. The experiment result shows that combine GQTS and MA can find better strategies that outperform other normal strategies. The performance of remuneration indicates that the trading system is enhanced with a year-on-year sliding window and 2-phase sliding window.

Keywords: Decision Support Systems, Service Systems and Organization
Abstract: With the development of IoT technology, it has become possible to accumulate and regularly measure multidimensional time-series data. In this study, we focus on the usage of multidimensional time-series data from printer products’ log data and propose a method for its analysis. In addition to the number of sheets printed by each customer, the log data includes various time-series information such as the amount of remaining toner, the number of stoppages that occur, and the activation times. To utilize these data for business purposes, it is desirable to construct a model for predicting future changes in use characteristics for each customer. In this study, we apply the random forest algorithm to predict such changes. However, if all measurable features of the problem are included, the model becomes complex and cannot be interpreted. Although the accuracy is relatively high if an appropriate learning algorithm is applied, the complex model tends to overfit the training data. In this paper, we propose a method to select the modeling features that can be interpreted by graph mining while maintaining accuracy. This would enable us to interpret the data at the field level and discover the hypotheses that are necessary for planned marketing policies. Finally, the proposed method is applied to real data and its efficacy is demonstrated.

Keywords: Decision Support Systems, Infrastructure Systems and Services, Model-based Systems Engineering
Abstract: Homelessness is a complex social problem and there have been limited attempts to use machine learning algorithms to understand the various issues that public health agencies would like to solve. For instance, it is important for the policy makers to know where homeless populations live so that they can provide necessary services accordingly. This article presents a satellite image tent-detection solution with three deep learning methods that utilize transfer learning from the ResNetV2, InceptionV3, and MobileNetV2 models, trained on ImageNet, attached to a unique architecture referred to as "TentNet". The performance of these models are first shown in detecting planes and ships within satellite imagery in previously defined datasets as a baseline. Then, a new dataset is created from a compilation of tents from the xView project to use for testing, along with another dataset of synthetic images from the generative adversarial networks StyleGAN2 and DCGAN for training. After training on a dataset containing only synthetic images for the tents class, the ResNetV2 architecture achieved the highest accuracy of 73.68% when testing on the real satellite imagery.

Keywords: Decision Support Systems
Abstract: The development of decision support systems is a growing domain that can be applied in the area of disease control and diagnostics. Using video-based surveillance data, skeleton features are extracted to perform action recognition, specifically the detection and recognition of coughing and sneezing motions. Providing evidence of flu-like symptoms, a decision support system based on causal networks is capable of providing the operator with vital information for decision-making. A modified residual temporal convolutional network is proposed for action recognition using skeleton features. This paper addresses the capability of using results from a machine-learning model as evidence for a cognitive decision support system. We propose risk and trust measures as a metric to bridge between machine-learning and machine-reasoning. We provide experiments on evaluating the performance of the proposed network and how these performance measures can be combined with risk to generate trust.

Keywords: Decision Support Systems, Conflict Resolution, Enterprise Information Systems
Abstract: A recurring problem for energy supply companies is the guarantee of the quality of services, which in many cases is regulated. Even so, there are a large number of lawsuits against energy distribution companies, for several reasons, increasing the operating costs of these companies, in many situations with cases that could be resolved via negotiation. This work proposes a method to predict legal judgment outcome, regarding the chance of being won or lost by the company. The idea is to understand in which lawsuits more effort should be made to conduct a negotiation outside the court. The methodology is divided into 5 stages: feature extraction, sampling with Borderline SMOTE, feature encoding with Target Encoding, classification with XGBoost, and evaluation. The proposed method was evaluated in a database with more than seventy thousand lawsuits, with different outcomes and types, reaching an accuracy of 78.13%, F1 of 74.34%, and AUC of 77.59%.

Keywords: Decision Support Systems, Conflict Resolution, Enterprise Information Systems
Abstract: A recurring problem for energy supply companies is the quality of guarantees service that is regulated in many cases. Nevertheless, there are many lawsuits against energy distribution companies, for several reasons, which increase these companies' operating costs, in many situations with cases that could be resolved through negotiation. Hence, the main aim of this work is to construct an insightful tool for forecasting court outcomes for energy sector litigation focused on building features gathered from the client's historical partnership and key data for litigation utilizing eXtreme Gradient Boosting (XGBoost) as a classifier, TPE as an optimizer and feature engineering. The idea is to understand in which lawsuits more effort should be made to conduct a negotiation outside the court. The proposed method is divided into three steps: (1) data acquisition; (2) feature engineering; (3) classification and optimization when evaluated with a dataset of over 70 thousand lawsuits, with 81 different outcomes reaching TOP-3 accuracy of 84.08%.

Keywords: Enterprise Information Systems, Enterprise Architecture & Engineering
Abstract: Regression testing for database application is a costly task because frequently treats with large databases and complex SQL statements. Therefore, some works select a subset of the database for testing purpose, i.e. shrink database creating a test database and thus improving the efficiency of the testing. But normally test data selection is also a complex optimization problem. So, this work proposes a test data selection method for SQL regression testing based on mutation, called MutShrink (Mutation-based Test Database Shrinking Method). The goal is minimizing the testing cost reducing database while keeping the similar effectiveness of original database. We performed experiments using a benchmark with some complex SQLs and large database. We compared our proposal against the baseline QAShrink tool and results revealed that our proposal outperformed QAShrink tool in 92.85% of cases when evaluated by Mutation Score metric, and in 57.14% of cases when assessed by Full Predicate Coverage metric.

Keywords: Infrastructure Systems and Services, Enterprise Information Systems, Distributed Intelligent Systems
Abstract: Smart power grids are one of the most complex cyber-physical systems, delivering electricity from power generation stations to consumers. It is critically important to know exactly the current state of the system as well as its state variation tendency; consequently, state estimation and state forecasting are widely used in smart power grids. Given that state forecasting predicts the system state ahead of time, it can enhance state estimation because state estimation is highly sensitive to measurement corruption due to the bad data or communication failures. In this paper, a hybrid deep learning-based method is proposed for power system state forecasting. The proposed method leverages Convolutional Neural Network (CNN) for predicting voltage magnitudes and a Deep Recurrent Neural Network (RNN) for predicting phase angels. The proposed CNN-RNN model is evaluated on the IEEE 118-bus benchmark. The results demonstrate that the proposed CNN-RNN model achieves better results than the existing techniques in the literature by reducing the normalized Root Mean Squared Error (RMSE) of predicted voltages by 10%. The results also show a 65% and 35% decrease in the average and maximum absolute error of voltage magnitude forecasting.

Keywords: Enterprise Information Systems, Cyber-Physical Cloud Systems
Abstract: This paper introduces the concept of product biography information system (PBIS). The findings emerge from a design science research project conducted in a paper pulp company integrating the PSI-20 stock market index of Euronext Lisbon. The results include a reference architecture and design principles for the development of PBIS supported by blockchain and multiple generations of digital twins. For theory, PBIS offers an extension to product lifecycle management, ensuring that products lives are memorized in its sociomaterial context of production, logistics, and use. For practice, we show how organizations can design new enterprise systems that capture complex product biographies taking advantage of Industry 4.0. The findings are relevant for the innovation of product-service systems that adhere to the emerging challenges of sustainable development and traceability.

Keywords: Model-based Systems Engineering, Enterprise Information Systems
Abstract: Business rules are used to define or limit certain aspects of business. While they should be understandable for different interested parties, including business analysts, end-users, programmers, or testers, it is also highly recommendable that computers efficiently process them. Business rules can be expressed using different languages (styles), potentially influencing their quality. The main aim of this research is to determine which of the business rule specification notations used at early stages of software development (CIM level) is the best for different groups of recipients. The paper presents the results of the experiment designed to compare the usability of two business rule specification languages: SBVR SP (Polish version of SBVR SE), and RuleSpeak. These languages have very similar expressiveness and scope of application. Both introduce some restrictions on word order (grammar) and expressions used. Their usability was assessed from three perspectives: effectiveness, efficiency, and satisfaction. The study was conducted on three groups of participants representing various user groups. It occurred that SBVR SP is more useful than RuleSpeak.

Keywords: Intelligent Green Production Systems, Systems Biology, Technology Assessment
Abstract: Citrus detection is an essential component of the citrus industry. In order to realize the identification, positioning, segmentation, maturity estimation, and quality evaluation of citrus in complex environments, this paper proposes a multi-task deep learning network that can be applied to multiple scenes for citrus detection. The system is based on the Mask R-CNN network framework. By adding multi-task branches, modifying model parameters, and designing multi-task loss function, it can realize multi-task detection of citrus in a complex environment. The mAP on the validation set of the model obtained after training is 91.56%, and it takes an average of 0.35s to detect a citrus image using GeForce GTX 1080 Ti. Through the comparative analysis of the detection effect and performance evaluation index F value of multi-task citrus under different maturity, quality, citrus quantity, and light angle, the experimental results show that the model can effectively and accurately detect the citrus with different maturity and quality in the environment of citrus fruit overlap, tree branch and leaf occlusion, light change and surface shadow.

Keywords: Intelligent Assistants and Advisory Systems, Model-based Systems Engineering
Abstract: Requirements define the problem boundaries within which an engineering team tries to find acceptable solutions. Gaps in requirements formulation can lead to solutions that are not fit-for-purpose. However, the completeness of a set of requirements cannot be demonstrated; rather, completeness is an attempt, a best-effort pursuit. In current practice, where requirement gaps are frequent in system development, the human (engineer or team of engineers) becomes a major factor in the comprehensiveness of the resulting set of requirements. In this paper, we present a concept of an intelligent systems engineering (SE) advisor that supports the (human) engineer in identifying gaps as requirements are formulated, the set of structural rules that the intelligent SE advisor uses to perform the assessment, and a proof-of-concept implemented as a plugin for a Systems Modeling Language (SysML) software environment. The proposed intelligent SE advisor evaluates requirements that are formulated in the form of models leveraging a knowledge repository to read the model-based requirements. If potential gaps in the set of requirements are identified, these are presented to the engineer, who decides how to address the gaps. In this way, the intelligent SE advisor contributes to assessing requirements validation, beyond simply verifying model construction.

Keywords: Decision Support Systems, Intelligent Assistants and Advisory Systems
Abstract: K-Nearest Neighbors (KNN) has remained one of the most popular methods for supervised machine learning tasks. However, its performance often depends on the characteristics of the dataset and on appropriate feature scaling. In this paper, we explore characteristics of a dataset that make it suitable for being used within KNN. As part of this, two new measures for dataset dispersion, called mean neighborhood target standard deviation (MNTSD), and mean neighborhood target entropy (MNTE) are formulated to determine the expeced performance while using KNN regressors and classifiers, respectively. It is empirically demonstrated that these measures of dispersion can be indicative of the performance of KNN regression and classification. This idea is further used to learn feature weights that help improve the accuracy of KNN classification and regression. For this, it is argued that the MNTSD and MNTE, when used to learn feature weights, cannot be optimized using gradient-based optimization methods and we develop optimization strategies based on metaheuristic methods, namely genetic algorithms and particle swarm optimization. The feature-weighting method is tried in both regression and classification contexts on publicly available datasets, and the performance is compared to KNN without feature weighting. The results indicate that the performance of KNN with appropriate feature weighting leads to better performance.

Keywords: Intelligent Power and Energy Systems
Abstract: Nowadays, multi-core processing systems have to perform complex functionalities on densely packed multi-million gate platforms, which makes such systems prone to uncontrolled surges in core temperatures, if not effectively controlled. Increasing temperature above specified limits not only leads to high cost of cooling but also results in higher dissipation of leakage power together with a reduction in performance and lower system life expectancy. In this work, we propose a two-level low-overhead proportional fair resource allocation strategy called TEARS: A temperature-aware real-time scheduler for heterogeneous multi-core systems, for scheduling of periodic tasks with bounded number of migrations and context-switches. The proposed algorithm's first level divides time into distinct windows based on deadlines of tasks, so that exact proportional fairness is maintained at all window boundaries. The second level accomplishes intra-window scheduling with the aim of maximising the use of resources while not breaching a specified thermal threshold. Our experimental analysis shows that the presented strategy not only improves upon the state-of-the-art in terms of resource utilisation (as high as 16.09%) but also reduces average temperatures of cores in the system.

Keywords: Decision Support Systems, Intelligent transportation systems, Smart urban Environments
Abstract: The vehicular service support with adaptability, real-time, and low delay is crucial for connected vehicles. However, due to limited coverage of mobile edge computing servers and data processing capability of connected vehicles, vehicular services need to be offloaded to the edge server and adaptively migrate as the connected vehicle moves. Aiming at the adaptive migration service, a deep Q-learning service migration decision algorithm is proposed in this paper. The proposed algorithm can dynamically adjust the vehicular service migration decision according to traffic information. Furthermore, a service migration framework consisting of neural networks is proposed in this paper to improve the adaptability and real-time performance of the algorithm. By using this framework, training and decision-making can be carried out simultaneously in different places. Finally, compared with the two existing algorithms, extensive simulations are conducted to verify the effectiveness of the proposed algorithm.

Keywords: Intelligent transportation systems, Distributed Intelligent Systems, Decision Support Systems
Abstract: The aim of this paper is to describe our proposed ABOS framework (Agent-Based Optimization Systems) by demonstrating the interest in using the multi-agent approach while operating hybrid metaheuristics to solve Combinatorial Optimization Problems (COP). Two main contributions are highlighted in this work: 1) to show that the alliance of the multi-agent systems (MAS) and the metaheuristics, based on the interaction and the parallelisms concepts, facilitates the hybrid metaheuristics development and allows the simultaneous exploration of different regions of the search space and 2) to demonstrate that the use the multi-agent approach, in the context of optimization, is a crucial option in the process of hybridization allowing the development of generic structures. These later promote the interaction between metaheuristics independent of the problem to be addressed. Our challenge in this ABOS framework is to endow the participant agents, with a set of rational behaviours allowing them to change in real time their strategies, according to the optimization process evolution. The simulation results show that the collaborative optimization can be effective in some cases, hence the need to set effectively the parameters of the optimization algorithms behaviours and the collaborative protocols. We also demonstrate that the use of ABOS framework with MAS allows a more robust and generic structure, capable with minimal changes handling different COP.

Keywords: Intelligent transportation systems, Smart urban Environments, System of Systems
Abstract: Public transportation in cities in the U.S. is experiencing a period of regrowth but may be unsustainable and blind to community needs and policies. While much of the public transportation research is focusing on subways and light rail, bus systems are often the only financially feasible transportation options for many mid-level cities. Smart city and smart transportation technologies can help to improve public bus transportation, but these technologies can also ignore the community, policy, and environmental issues. This literature review identifies applicable research in smart transportation technologies with consideration to aspects of technology, policy, community, and environment. The review finds that recognition of each aspect is not yet equally valued. Each aspect needs to be equally valued and addressed in order to create long term technology solutions that address policy, community, and environment.

Keywords: Intelligent transportation systems, Intelligent Learning in Control Systems, Smart urban Environments
Abstract: Adaptive traffic signal control is one key avenue for mitigating the growing consequences of traffic congestion. Incumbent solutions such as SCOOT and SCATS require regular and time-consuming calibration, can't optimise well for multiple road use modalities, and require the manual curation of many implementation plans.

A recent alternative to these approaches are deep reinforcement learning algorithms, in which an agent learns how to take the most appropriate action for a given state of the system. This is guided by neural networks approximating a reward function that provides feedback to the agent regarding the performance of the actions taken, making it sensitive to the specific reward function chosen. Several authors have surveyed the reward functions used in the literature, but attributing outcome differences to reward function choice across works is problematic as there are many uncontrolled differences, as well as different outcome metrics.

This paper compares the performance of agents using different reward functions in a simulation of a junction in Greater Manchester, UK, across various demand profiles, subject to real world constraints: realistic sensor inputs, controllers, calibrated demand, intergreen times and stage sequencing. The reward metrics considered are based on the time spent stopped, lost time, change in lost time, average speed, queue length, junction throughput and variations of these magnitudes. The performance of these reward functions is compared in terms of total waiting time. We find that speed maximisation resulted in the lowest average waiting times across all demand levels, displaying significantly better performance than other rewards previously introduced in the literature.

Keywords: Intelligent transportation systems, System of Systems, Model-based Systems Engineering
Abstract: The complexities associated with Automated Driving Systems (ADSs) and their interaction with the environment pose a challenge for their safety evaluation. Number of miles driven has been suggested as one of the metrics to demonstrate technological maturity. However, the experiences or the scenarios encountered by the ADSs is a more meaningful metric, and has led to a shift to scenario-based testing approach in the automotive industry and research community. Variety of scenario generation techniques have been advocated, including real-world data analysis, accident data analysis and via systems hazard analysis. While scenario generation can be done via these methods, there is a need for a scenario description language format which enables the exchange of scenarios between diverse stakeholders (as part of the systems engineering lifecycle) with varied usage requirements. In this paper, we propose a two-level abstraction approach to scenario description language (SDL) – SDL level 1 and SDL level 2. SDL level 1 is a textual description of the scenario at a higher abstraction level to be used by regulators or system engineers. SDL level 2 is a formal machine-readable language which is ingested by testing platform e.g. simulation or test track. One can transform a scenario in SDL level 1 into SDL level 2 by adding more details or from SDL level 2 to SDL level 1 by abstracting.

Keywords: Smart urban Environments
Abstract: The Spatio-temporal scale varying characteristics of aridity and thus the dominance of this method within the present year is notable due to global climate change during this investigation, we proposed to work out the trend of the Aridity index using non-parametric methods like Mann-Kendall and Sen's slope approaches for testing. In Contrast, the Aridity index is computed by using Jensen formula to formulate, which is worldwide accepted. At the same time, ETo can be calculated using the well-known scheme by the Food and Agriculture Organization (FAO) through Penman-Monteith FAO-56 (PM). We used ten years of data (2000–2 009) of 12 climate locations positioned in Khyber Pakhtunkhwa (KP) Province, Pakistan. We acknowledged an increasing drift within the Aridity index rate had been observed mostly in spring, summer, and winter, with a downward tendency through fall. Furthermore, the statistical investigation demonstrations an increasing drifts in AI during spring and winter. In conclusion, we presented an efficient procedure which may, therefore, benefit by including in irrigation, water resource management, and meteorological modeling for future enlargement.

Keywords: Distributed Intelligent Systems, Intelligent Assistants and Advisory Systems
Abstract: On a daily basis people waste so many items, and what better way to help them from wasting but to create an app that tracks their groceries, creates less waste in the world and saves money at the same time. People waste food on average 1 pound per person each day they live. The application GAPP will cut down costs and waste in everyday life. People also misplace or lose track of items daily. Location of items is a big deal and knowing where they are at all times on a device would help.

Keywords: Model-based Systems Engineering, Intelligent Assistants and Advisory Systems, System of Systems
Abstract: Machine learning (ML) based prediction models proved to be fast, accurate, and free from human errors with capabilities to address pressing problems in healthcare. Being progressive in nature, Chronic Obstructive Pulmonary Disease (COPD) patients require frequent hospital readmission. Frequent hospital readmission, may be preventable, is a patient-centric approach which result in expensive health services and poor utilization of overly-burdened medical resources in recent times. In this research study, we envisaged a ML-based model to predict hospital readmission in 30-day by analyzing daily physical activity (PA) data with an accelerometer-based wrist-worn device. Prediction models based on logistic regression, lasso regularization, and MLP deep neural network have been used for training and testing PA data. For analysis, 70% of PA data used for training and 30% for testing and predicting readmission. Readmission predicted with sensitivity 0.88, positive predictive value 0.75, false positive 0.25 and area under ROC curve 0.50. The novelty our approach is to predict hospital readmission by monitoring health condition with accelerometer-based wrist-worn device which generate PA data electronic in nature, can be readily employed with various e-healthcare services. Therefore, we propose to develop a cloud-based system, coordinated & aligned with local-health services and e-healthcare, to provide better patient care system and alarming notifications; and to reduce preventable hospital readmission to cut medical expenses and conserve medical resources for better patient care and readily available medical services for all.

Keywords: Systems Biology, Systems Medicine
Abstract: The seismocardiography (SCG) is one of the noninvasive diagnostic approaches to detect the heart disease such as valvular heart disease (VHD) or heart failure (HF). The lack of operational guidelines to identify the SCG feature points in the signal waveform made the investigation of SCG feature-point-labeled template be one of the essential topics in SCG researches. For this reason, a new SCG template generation method was studied and proposed in this article. The new method leveraged the clustering skill of K-means algorithm and the waveform alignment capability of the dynamic time warping (DTW) algorithm. The merits of using the new method are the flexibility to average cardiac signal segments with different data lengths and the alleviation of the flattened template problem which often bother the conventional ensemble average method. The strategies to achieve the global minimum of the cost function in K-means clustering, to recognize the clustered groups and to improve the warping criteria for DTW averaging were addressed. Experimental results demonstrated the capabilities on the extraction of the frequent appearing SCG waveforms and the generation of DTW averaged templates from the clinical data of 16 subjects (8 healthy subjects and 8 heart failure subjects). The pros and cons of using DTW based averaging were compared with those of using conventional ensemble averaging.

Keywords: Agent-Based Modeling, Cybernetics for Informatics
Abstract: In order to properly teach any subject, it is important to understand the underlying cognitive models of the learning process. Unfortunately, sometimes basic concepts are not adequately taught during primary school because primary school teachers lack the knowledge and/or the basic tools about these concepts. For instance, children have to learn to handle our standard base-10 positional numeral system. Unfortunately, teachers are not usually aware of the intrinsic difficulties of this learning process, the reason being that adults have internalized this knowledge so deep in their mental process that they usually think that it is an obvious and very natural representation. Thus, teachers have problems to understand the actual difficulties that children must confront. In this paper we present an experience we have conducted in the Education Faculty of our university to help future teachers to understand such difficulties. By using our tool, future teachers are forced to face all the steps children have to follow in their learning process. Thus, they learn the problems their future students will have, and they will be better prepared to improve the Mathematics skills of their students.

Keywords: Biometric Systems and Bioinformatics
Abstract: Reinforcement learning (RL)-based brain-machine interfaces (BMIs) obtain the mapping between neural activities and the subject’s intention using reward. The advantage is to allow subjects to learn to control the external device without real limb movements. Internal-reward-based RL-BMIs train the decoder based on the reward information extracted from neural activities, which is a step towards autonomous BMI design. Studies have used medial prefrontal cortex (mPFC) activity to extract the internal reward when rodents are in the learning process. However, the reward and non-reward classification using single neuron spikes is noisy. In this paper, we explore the reward interpretation ability on the high-frequency bands of local field potentials (LFPs) in the mPFC area and investigate whether LFPs contain extra information over spikes by using support vector machine (SVM) as the classifier to distinguish the rewarding and non-rewarding trials. We find that among the three bands, namely, gamma (30–80Hz), high-gamma (80–200Hz) and bhfLFP (200–400Hz), the bhfLFP band has the highest decoding accuracy (86.97% for a high lever task and 79% for a low lever task). Compared with the spike only, the integrated LFP-spike feature has comparable or better decoding performance. It potentially provides more stable internal reward for RL-based BMIs. Keywords— reinforcement learning, brain machine interface, internal reward, local field potentials (LFPs)

Keywords: Computational Intelligence, Information Assurance & Intelligent, Knowledge Acquisition in Intelligent
Abstract: Autonomous decision-making is a central challenge to theories and technologies of AI and computational intelligence. It could not be implemented because the inexhaustive, indeterministic, and uncertain bottlenecks in traditional machine inference theories. This paper presents a formal study on mathematical models of decision and decision-making. Generic mathematical models of formal decisions are created for qualitative, quantitative, and serial decision-making. Cognitive algorithms are developed to extend traditional intuitive, empirical, or heuristic decisions to machine-learnt inferences for decision making. Experiments have demonstrated the power of cognitive decision-making algorithms and technologies for autonomous systems and computational intelligence.

Keywords: Knowledge Acquisition in Intelligent, Machine Learning, Computational Intelligence
Abstract: One of the key challenges to AI is autonomous Decision Making (DM). This paper strives towards a formal approach to model cognitive DM in order to enable AI machines to conduct autonomous DM. On the basis of the theoretical models for rational decisions and rigorous DM developed in our Lab, we implement a set of algorithms for autonomously handling primitive, single, and serial decisions rigorously. An autonomous DM supporting tool is designed and implemented based on the algorithms. Experiments on various decision problems have demonstrated the capability of the tool and the methodology in many cases beyond those of human DM outcomes in both complexity and speed.

Keywords: Biometric Systems and Bioinformatics, Computational Intelligence, Machine Learning
Abstract: A typical biometric system aims to recognize individuals based on their unique physiological or behavioral traits. Online Social Networking (OSN) platforms have become an integral part of the daily life of individuals, where they leave a recognizable trail of behavioral information. Social Behavioral Biometric (SBB), being an emerging trend, focuses on such trails to distinguish between individuals. This research investigates the impact of users' writing profiles on OSN to conclude whether such profiles contribute to SBB. The distinctiveness of the SBB features that are extracted from the social behavioral data of Twitter is studied. A person identification system that relies on the writing profiles of OSN users is proposed. The developed system is cross-validated on a social interaction database of 241 Twitter users. The rank-1 identification rate from users' writing profiles is 91.70% and the rank-8 identification rate is 99%. Furthermore, the experimental results establish that the users' writing profiles have the highest impact over other social biometric features.

Keywords: Computational Intelligence, Cybernetics for Informatics, Intelligent Internet Systems
Abstract: Missing data imputation is a critical part of data cleaning tasks and vital for learning from incomplete data. This paper proposes a novel cooperative clustering imputation (CCI) method to estimate missing values. The proposed method aims to find a better clustering model and donor for imputation, comparing with individual clustering algorithms. It makes use of agreements among different clustering algorithms to generate a set of sub-clusters, and, then, merges these sub-clusters based on the matrix of the performance measures of sub-clusters. The proposed method is evaluated using ten public datasets from UCI data repository and V2X communication data with induced missing samples, and compared with three standard clustering based imputation methods, k-means imputation, fuzzy c-means imputation, and partition around medoids imputation. Missing values are induced through each dataset by different missing mechanisms, missing rates, and missing distribution, and, thus, various incomplete datasets are generated. The performance of these methods are checked using normalized root mean square error (NRMSE). The attained experimental results indicate the effectiveness of the proposed missing values imputation method.

Keywords: Computational Intelligence, Heuristic Algorithms, Optimization
Abstract: Many ever-increasingly complex engineering optimization problems fall into the class of High-dimensional Expensive Problems (HEPs), where fitness evaluations are very time-consuming. It is extremely challenging and difficult to produce promising solutions in high-dimensional search space. In this paper, an Autoencoder-embedded Evolutionary Optimization (AEO) framework is proposed for the first time. As an efficient dimension reduction tool, an autoencoder is used to compress high-dimensional landscape to informative low-dimensional space. The search operation in this low-dimensional space can facilitate the population converge towards the optima more efficiently. To balance the exploration and exploitation ability during optimization, two sub-populations coevolve in a distributed fashion, where one is assisted by an autoencoder and the other undergoes a regular evolutionary process. The information between these two sub-populations are dynamically exchanged. The proposed algorithm is validated by testing several 200 dimensional benchmark functions. Compared with the state-of-art algorithms for HEPs, AEO shows extraordinarily high efficiency for these challenging problems.

Keywords: Computational Intelligence, Machine Learning
Abstract: A common problem in machine learning is to find representative real-world labeled datasets to put the methods to test. When developing approaches to deal with concept drifts, some datasets such as the Forest Covertype and Nebraska Weather are common choices for testing, even though there is no consensus on whether these exhibit concept drifts or not. We argue that some well-known real-world concept drift datasets present a high serial dependence in the target class and may have only minor changes. With this in mind, we propose the use of naïve methods that should be used for comparison with methods that deal with concept drifts. The experimental results using six real-world well-known concept drift datasets show that the naïve approaches can be better than some methods to deal with possible concept drifts in datasets such as the Forest Covertype, Electricity, and Nebraska Weather. These results suggest that some widely used datasets may be trivial from the concept drift standpoint, and thus, should be avoided, or at least the results should be compared with the proposed naïve methods.

Keywords: Computational Intelligence, Machine Learning
Abstract: This paper proposes a hybrid ensemble learning approach that combines statistical and data stream mining algorithms to obtain better forecasting performance in multiple time series prediction problems. Although some multiple time series algorithms perform surprisingly well in a variety of domains, it is well-known that no one is dominant for every existent domain. Therefore, we developed a meta-technique based on data stream mining and static ensemble selection strategy and evaluated its forecasting goodness-of-fit in time series datasets from M3 and M4 competitions. After training different regression models, we show how the combination of auto.arima and AdaGrad leads to improved forecasting rates, thus surpassing the results of state-of-art algorithms.

Keywords: Computational Intelligence, Neural Networks and their Applications, Optimization
Abstract: Recent years have witnessed the success of deep learning in many fields. Commonly, the deep neural networks are trained by gradient-based methods, which is however ineffective in some cases when the optimization landscapes contain many local optima. In this study, we propose a novel optimization approach that combines neuroevolution with gradient-based method, which possesses the advantages of global search and fast convergence. The main challenge is the high expense of network training, especially when the network structure becomes deeper. This motivates us to utilize the concept of transfer learning which borrows knowledge from a source domain to enhance the learning ability in a target domain. Unfortunately, the design of transfer learning strategies for specific scenarios usually requires external expert knowledge. We therefore propose an adaptive transfer system (ATS) based on dataset similarity, which adaptively adjusts the transferring and retraining modules according to the similarity of the source and target tasks. Empirical studies on image classification problems demonstrate the effectiveness of the proposed algorithm. We are the first attempt to show that the neuroevolution can be successfully applied to deep transfer learning.

Keywords: Computational Intelligence, Evolutionary Computation
Abstract: In Pareto based multi- and many-objective evolutionary algorithms (MOEAs and MaOEAs), non-dominated sorting is an important step that divides the set of solutions into different disjoint non-dominated fronts. In the last 20 years, there have been various approaches proposed for non-dominated sorting. Recently, an approach known as Dominance Degree Approach for Non-Dominated Sorting (DDA-NS) has been proposed. This approach guarantees that the number of floating-point comparisons is always bounded by O(MN log N) for N solutions and M objectives, which is not true for various approaches. However, the worst-case time complexity of DDA-NS is recently proved to be Theta(MN^2+N^3). In this paper, we develop an approach on the top of DDA-NS, which also guarantees O(MN log N)} floating-point comparisons and its worst-case time complexity is proved to be Theta(MN^2) as opposed to Theta(MN^2+N^3) of DDA-NS.

Keywords: Computational Intelligence, Evolutionary Computation
Abstract: Finding preferred solutions is important for DMs to take the next step in solving Multi-objective optimisation problems (MOPs). When no specific preferences are available, knee point(s) are typically considered to be the most preferred solutions in multi-criterion decision-making since their smallest trade-off loss at all objectives. Knee point(s), including concave, convex and edge knee point(s), can reflect some geometry characteristics of the given non-dominated solutions because of its unique location. However, most of contemporary research for knee point identification (KPI) is only designed for convex knee point(s). Based on Voronoi diagram which can effectively reflect the distribution of the given set, we propose a method to identify all three types of knee points from a geometry view. In order to validate our method, we compare the performance of our method with other three state of the art approaches on benchmark problems for knee point identification. Experimental results fully show the effectiveness and competitiveness of our proposed KPI method based on Voronoi diagram (KPIVD) for identifying three types of knee points.

Keywords: Evolutionary Computation
Abstract: In the evolutionary multi-objective optimization (EMO) community, it is usually assumed that the final population is presented to the decision maker as the result of the execution of an EMO algorithm. Recently, an unbounded external archive was used to evaluate the performance of EMO algorithms in some studies where a pre-specified number of solutions are selected from all the examined non-dominated solutions. In this framework, which is referred to as the solution selection framework, the final population does not have to be a good solution set. Thus, the solution selection framework offers higher flexibility to the design of EMO algorithms than the final population framework. In this paper, we examine the design of the multi-objective evolutionary algorithm based on decomposition (MOEA/D) algorithm under these two frameworks. First, we show that the performance of MOEA/D is improved by linearly changing the reference point specification during its execution through computational experiments with various combinations of initial and final specifications. Robust and high performance of the solution selection framework is observed. Then, we examine the use of a genetic algorithm-based offline hyper-heuristic method to find the best configuration of MOEA/D in each framework. Finally, we further discuss solution selection after the execution of an EMO algorithm in the solution selection framework.

Keywords: Evolutionary Computation
Abstract: In general, performance comparison results of optimization algorithms depend on the parameter specifications in each algorithm. For fair comparison, it may be needed to use the best specifications for each algorithm instead of using the same specifications for all algorithms. This is because each algorithm has its best specifications. However, in the evolutionary multi-objective optimization (EMO) field, performance comparison has usually been performed under the same parameter specifications for all algorithms. Especially, the same population size has always been used. In this paper, we discuss this practice from a viewpoint of fair comparison of EMO algorithms. First, we demonstrate that performance comparison results depend on the population size. Next, we explain a new trend of performance comparison where each algorithm is evaluated by selecting a pre-specified number of solutions from the examined solutions (i.e., by selecting a solution subset with a pre-specified size). Then, we discuss the selected subset size specification. Through computational experiments, we show that performance comparison results do not strongly depend on the selected subset size while they depend on the population size.

Keywords: Evolutionary Computation
Abstract: In the evolutionary multi-objective optimization (EMO) community, hypervolume (HV) has been frequently used to evaluate the performance of EMO algorithms. The HV is a Pareto compliant indicator which can simultaneously evaluate both the convergence of solutions to the Pareto front and their diversity. No other Pareto compliant indicator is known. In the EMO community, it is implicitly assumed that a set of uniformly distributed solutions over the entire Pareto front including its boundary has the best HV value. This is true for a linear Pareto front of a two-objective problem when a reference point for HV calculation is not too close to the Pareto front. In this paper, we numerically examine this issue for three-objective problems. We perform computational experiments to search for the optimal distribution of a small number of solutions for HV maximization. This is to visually explain the characteristic features of the optimal distribution. Our experimental results clearly show that a set of uniformly distributed solutions is not always optimal for HV maximization. It is also shown that the optimal distribution for HV maximization is often inconsistent with our intuition. For example, a set of ten solutions systematically generated by Das and Dennis method is not optimal.

Keywords: Heuristic Algorithms
Abstract: When the traditional heterogeneous multi-core scheduling algorithm performs tasks with high resource density, a large amount of idle time often occurs on the processor core.Therefore,based on the environment of heterogeneous multi-core processors, this paper studies the static heuristic table scheduling algorithm, and proposes an optimization approach for the problem of single priority assignment and too simple task assignment. We design optimization in the static heuristic scheduling algorithm list generation phase and task allocation phase, and propose a hybrid task allocation method with three strategies to improve the standby time utilization of processor core. Then, DVFS technology is used to optimize the scheduling results, so that the task can run with lower energy consumption without increasing makespan. Finally, the new algorithm is compared with three traditional scheduling algorithms through design experiments, and it is proved that the new algorithm has better performance when executing more tasks.

Keywords: Heuristic Algorithms, Artificial Life, Computational Intelligence
Abstract: Surveillance is a canonical task for robotics, so it is one of the most popular activities for a wide range of problems for robots. The problem's complexity increases proportionally with the number of rooms because the robot must act avoiding obstacles, saving time and energy. The proposed algorithms employ a combination of different search techniques to control a robot during a surveillance task. Our inspiration came from the possibility to use a discrete model employing a cellular automata combined with different heuristics approaches. This improvement of the best path selection was performed due to A* search optimization. Then, for solving collision problems a cellular automata rule is used in the expansion of obstacles, for a collision-free path. Finally, the surveillance task was implemented in a simulator called V-REP using e-Puck architecture. Simulation and experimental results indicate that this surveillance task could be implemented in low-cost architectures in a simplified way. The novelty consists of implementing these techniques in a realistic robot simulator, and also of a systematic analysis of each heuristic function used in contrast to the data structure optimization algorithm proposed herein.

Keywords: Heuristic Algorithms, Optimization
Abstract: The routing and wavelength assignment (RWA) problem is a classic and challenging problem in wavelength-division multiplexing (WDM) optical networks and has been shown to be NP-hard. This paper studies the min-RWA problem with the objective of minimizing the number of required wavelengths by presenting a new powerful neighborhood called Shift-and Shaking (SAS). The proposed SAS integrates a high-level shift move to change the wavelength of one lightpath and two low-level ejection chain-based shaking (ECS) procedures to find the best routings for the related lightpaths. This new neighborhood is embedded into a simple iterated local search algorithm, called SAS-ILS, for solving the min-RWA problem. The proposed SAS-ILS is tested on three sets of totally 113 widely studied instances in the literature. Comparison with other state-of-the-art algorithms shows that the SAS-ILS is able to improve 22 previous best known results, while matching the best known results for the remaining ones within short computational time.

Keywords: Heuristic Algorithms, Optimization, Evolutionary Computation
Abstract: Several real-world optimization problems manipulate discrete variables, involve with many objectives and vary along the time, that is, they are dynamic. Recent works have focused on investigate dynamic multiobjective optimization problems (DMOPs), which adds an additional challenge to the search convergence. Some evolutionary strategies have emerged based on the adaptation of consagrated multiobjective algorithms previously proposed for static continuous optimization problems, such as, NSGA-II and MOEA/D. This work presents a novel evolutionary algorithm for dynamic discrete many-objective problems named D-MEANDS. It uses the subjacent search proposed in MEANDS. This algorithm has been successfully investigated in static MOPs and herein we propose some adaptations to be used in DMOPs. A comparative analysis of the new proposal is made using two DMOP evolutionary algorithms from the literature: DNSGA-II and MS-MOEA. A dynamic many-objective version of the knapsack problem (KP), known as dynamic multiobjective knapsack problem (DMKP), was explored. Results using DMKP formulations with 4 and 6 objectives sugest that D-MEANDS is a promising algorithm to deal with DMOPs with many objectives.

Keywords: Heuristic Algorithms, Optimization, Swarm Intelligence
Abstract: In this paper, we discuss the particle swarm optimization method (PSO) for global optimization, especially, a PSO using a perturbation-based chaotic updating system called PSO-SDPC. In this method, it is easy to select appropriate parameter values for effective search, and numerical experiments showed its good search ability. However, the search of the PSO-SDPC is not rotation-invariant because the perturbation terms of the chaotic updating system are added along the coordinate system of the standard basis, and the component-wise selection from the chaotic and the standard PSO updating systems for a particle's position deeply depends on the coordinate system. Therefore, in this paper, we improve the PSO-SDPC: the perturbations are added along a new coordinate system that is selected according to two best solutions, and all components of each particle's position are updated by the same system, which is selected from the two updating systems. Moreover, we show that the proposed method can be regarded as the rotation-invariant and keeps a high search ability through numerical experiments.

Keywords: Machine Learning
Abstract: Alzheimer's disease (AD) is one of the most common neurodegenerative diseases. Understanding AD progression can empower the patients in taking proactive care. Mini Mental State Examination (MMSE) and AD Assessment Scale Cognitive subscale (ADAS-Cog) are two prevailing clinical measures designed to evaluate the AD progression. In this paper, we propose a weakly supervised Temporal Multitask Matrix Completion (TMMC) framework, which combines a novel transductive multitask feature selection scheme, to simultaneously predict AD progression measured by MMSE and ADAS-Cog, and identify related biomarkers trackable of AD progression. Specifically, by treating the prediction of cognitive scores at each time point as a regression task, we first formulate AD progression problem as a standard Multitask Matrix Completion (MMC) model. Secondly, considering the limited number of samples available in this study, we introduce a transductive feature selection scheme to jointly select the task-shared features for multiple time points and the task-specific features for different time points, and thus alleviate the over-fitting defect caused by Small-Sample-Size issue. Thirdly, aiming at the small change of cognitive scores between successive time points for a patient, we employ a temporal regularization scheme to capture the temporal smoothness of cognitive scores. Furthermore, we design an efficient optimization algorithm based on Alternative Minimization and Difference of Convex Programming techniques to solve the proposed TMMC framework. Finally, the extensive experiments performed on real-world Alzheimer’s disease dataset demonstrate the effectiveness of our TMMC framework.

Keywords: Machine Learning, Computational Intelligence
Abstract: The financial credibility of a person is a relevant factor to determine whether a loan should be approved or not, and it is quantified by a credit score, which is computed using past performance on debt obligations, profiling, and other data available. Credit scoring becomes even a hotter topic in emerging countries, as interest rates and customer behavior swiftly vary, given the economic (in)stability of the country and as fintechs are chasing robust solutions for improved credit scoring solutions. Batch machine learning is often deployed for credit scoring, yet, they are tailored for static scenarios, i.e., they are not prepared to swiftly detect and adapt to changes in customer behavior, thus leading to slow recovery in such scenarios. In this paper, we bring forward an analysis on how batch machine learning can be combined with data stream mining techniques, thus leading to better recognition rates in credit scoring scenarios. We analyze three different real-world datasets from Brazilian financial institutions, whilst keeping their secrecy preserved, and show how batch and stream learning can be combined towards improved credit scoring systems, as well as highlighting relevant gaps that still require attention.

Keywords: Machine Learning, Computational Intelligence
Abstract: In the last decades, the development of generative/discriminative approaches for classifying different kinds of data has attracted scholars' attention. Considering the strengths and weaknesses of both approaches, several hybrid learning approaches which combined the desirable properties of both have been developed. Our goal in this paper is to combine Support Vector Machines (SVMs), as a powerful classification tool, and Bernoulli mixture model in order to classify binary data. We propose using Bernoulli mixture model for generating probabilistic kernels for SVM based on information divergence. These kernels make intelligent use of unlabeled binary data to achieve good data discrimination. We demonstrate the merits of the proposed hybrid learning approach for the problem of classifying binary and texture images.

Keywords: Machine Learning, Computational Intelligence
Abstract: Designing a reward function for Reinforcement Learning is tedious such that a new reward function needs to be uniquely designed for each environment. Self-Generation of Reward (SGR) solves this by making the agent creates its own reward from the changes in the surrounding, rather than being dependent to the reward produced by the environment. SGR achieved this by perceiving the changes using sensors, similar to how living things perceive the changes in environment in term of stimulus. The input from sensors are evaluated using Universal Sensor Evaluation Index (USEI), before converting it into rewards. Current USEI uses only strength and predictability evaluation, making the evaluation for danger detection inaccurate for certain environment. To create a more accurate evaluation, we proposed that time-based evaluation needs to be included in USEI. The performance for both previous and proposed evaluation index are tested using maze-like environment and Q-learning. Performances for both evaluation index are then compared against one another.

Keywords: Machine Learning, Evolutionary Computation, Swarm Intelligence
Abstract: Evaporation duct often appears in the near ground layer close to the sea surface, and it is an important factor affecting the performance of shore based, ship borne or low altitude airborne radar and communication systems. Mastering the information of evaporation duct in advance can effectively avoid the electromagnetic wave loss caused by the evaporation duct in the atmospheric environment. In this study, a regression algorithm based on empirical mode decomposition (EMD) and support vector regression (SVR) is proposed to solve the prediction problem of evaporation duct height (EDH). This paper introduces a method of extracting the data of EDH series, and splits the data of EDH series by EMD in spectrum and trains several instances of support vector regression machine to complete the prediction of each component. In addition, particle swarm optimization (PSO) and its variants are introduced to solve the parameter optimization problem of SVR. The experimental results demonstrate that the EMD strategy and particle swarm optimization strategy are effective to improve the accuracy of the prediction results.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition
Abstract: Palms alignment is an important work for palmprint recognition in uncontrolled environment. Many methods have made progress to achieve alignment. But most of them ignore the palm’s angles, which could not satisfy the alignment initialization when the hand has a large in-plane rotation. In this paper, we propose a palms alignment with affine transformation method based on a two-stage convolutional neural network (CNN). The basic idea is to rotate the target palm into the same angle category to avoid the following affine registration has a big matching error at the beginning. At the stage I, the given target palm is classified into two angle categories. At the stage II the upside down palm is firstly rotated 180 degrees, and then inputted into the subsequent feature extraction network, feature matching layer and regression network to achieve the affine alignment. Experimental results have proved the effectiveness of our method.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition, Biometric Systems and Bioinformatics
Abstract: This paper focuses on the instance segmentation of soft attributes on humans such as clothing and personal protective equipment at a hazardous workplace. We propose the use of soft biometric object classes from the Open Images V5 and DeepFashion2 datasets to pre-train a mask segmentation network to detect and segment personal protective equipment in the workplace. Preliminary results of our proposed model achieves a mean average precision, mAP₅₀, of 61.7% with minimal optimization, resulting in very good segmentation of construction helmets, high visibility vests, welding masks, and ear protection in the workplace. Applications of the results from this paper include improving workplace safety in hazardous industries by providing a tool to ensure proper personal protective equipment usage while maintaining worker anonymity.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition, Machine Vision
Abstract: Convolutional neural network (CNN) based clothing attribute recognition has been applied in many clothing-related applications, such as recommendation system and clothes retrieval. However, the outperformance of existing recognition approaches is limited on account of the requirement of manual spatial prior information, such as landmarks and bounding box. In this paper, we innovatively transfer existing instance-irrelative knowledge to our proposed method where salient prior information is employed to assist the attribute prediction to avoid such laborsome annotations. Concretely, we first propose a saliency-guided method composed of salient object detection network (SOD-N) and clothing attribute recognition network (CAR-N). %SOD-N generates saliency map as salient prior information for CAR-N to predict attributes. SOD-N provides the saliency map as the prior information guiding CAR-N to focus on the valid region. Furthermore, a new learnable fusion module is designed in CAR-N to aggregate the high-level features from the deep salient and clothing features. That can strengthen the ability of CAR-N to represent the correlative clothing attributes, resulting in further improving the final performance. The effectiveness of our method is demonstrated by the experimental results on clothing-related datasets, which improves among 1% to 10% mAP on each attributes category and almost 5% mean AP.