As of Aug. 2020, coronavirus disease 2019 (COVID-19) is still spreading in the world. In Japan, the Ministry of Health, Labour and Welfare developed “COVID-19 Contact-Confirming Application (COCOA),” which was released on June 19, 2020. By utilizing COCOA, users can know whether or not they had contact with infected persons. If those who had contact with infected individuals keep staying at home, they may not infect those outside. However, effectiveness decreasing the number of infected individuals depending on the app’s various usage parameters is not clear. If it is clear, we could set the objective value of the app’s usage parameters (e.g., the usage rate of the total populations) and call for installation of the app. Therefore, we develop a multi-agent simulator that can express COVID-19 spreading and usage of the apps, such as COCOA. In this study, we describe the simulator and the effectiveness of the app in various scenarios. The result obtained in this study supports those of previously conducted studies.

To achieve continuous frail care in the daily lives of the elderly, we propose AHOBO, a frail care robot for the elderly at home. Two types of support systems by AHOBO were implemented to support the elderly in both physical health and psychological aspects. For physical health frailty care, we focused on blood pressure and developed a support system for blood pressure measurement with AHOBO. For psychological frailty care, we implemented reminiscent coloring with the AHOBO as a recreational activity with the robot. The usability of the system was evaluated based on the assumption of continuous use in daily life. For the support system in blood pressure measurement, we performed a qualitative evaluation using a questionnaire for 16 subjects, including elderly people under blood pressure measurement by the system. The results confirmed that the proposed robot does not affect the blood pressure readings and is acceptable in terms of ease of use based on subjective evaluation. For the reminiscent coloring interaction, subjective evaluation was conducted on two elderly people under the verbal fluency task, and it has been confirmed that the interaction can be used continuously in daily life. The widespread use of the proposed robot as an interface for AI that supports daily life will lead to a society in which AI robots support people from the cradle to the grave.

Facial expression recognition (FER) has been widely researched in recent years, with successful applications in a range of domains such as monitoring and warning of drivers for safety, surveillance, and recording customer satisfaction. However, FER is still challenging due to the diversity of people with the same facial expressions. Currently, researchers mainly approach this problem based on convolutional neural networks (CNN) in combination with architectures such as AlexNet, VGGNet, GoogleNet, ResNet, SENet. Although the FER results of these models are getting better day by day due to the constant evolution of these architectures, there is still room for improvement, especially in practical applications. In this study, we propose a CNN-based model using a residual network architecture for FER problems. We also augment images to create a diversity of training data to improve the recognition results of the model and avoid overfitting. Utilizing this model, this study proposes an integrated system for learning management systems to identify students and evaluate online learning processes. We run experiments on different datasets that have been published for research: CK+, Oulu-CASIA, JAFFE, and collected images from our students (FERS21). Our experimental results indicate that the proposed model performs FER with a significantly higher accuracy compared with other existing methods.

To satisfy the increasingly demanding requirements in throughput and accuracy, more lightweight structures and a higher control bandwidth are highly desirable in next-generation motion stages. However, these requirements lead to a more flexible deformation, causing the estimation accuracy of the point of interest (POI) displacement to be guaranteed under the rigid-body assumption. In this study, a soft sensor model is constructed using a dynamic neural network (DNN) to estimate the POI displacement. This model can reflect the dynamic characteristics of the POI and realize accurate estimations. Moreover, a method combining stepwise and weight methods is proposed to analyze the influence of different DNNs, and a performance measure is presented to evaluate the soft sensor model. In the simulation, the DNN with the hidden feedbacks is proved to be the most suitable soft sensor model. The relative error and correlation coefficient obtained were less than 2% and 0.9998, respectively, during training and 5% and 0.9989, respectively, during testing. Compared with the data-driven model using the least-squares method, the proposed method exhibits a higher precision, and the relative error is within the setting range using the proposed performance measure.

This study investigates the consensus problem of second-order nonlinear multi-agent systems (MASs) with actuator faults via a sliding mode control approach. The consensus error dynamic is given based on the relative states of the neighbors. Then, a sliding mode surface based on consensus errors is proposed, and the asymptotic stability of the sliding mode is proved using the Lyapunov theory. Furthermore, a sliding-mode fault-tolerant consensus protocol is proposed to compensate for actuator faults. According to the sliding mode control theory, the proposed sliding-mode fault-tolerant controller ensures that the consensus of the MASs can be reached in a finite time. Finally, a simulation example of a second-order multi-robot system is presented to demonstrate the effectiveness of the proposed controller.

Time delay exists in image-based visual servo system, which will have a certain impact on the system control. To solve the impact of time delay, the time delay compensation of the object feature point image and the image Jacobian matrix is discussed in this paper. Some work is done in this paper: The estimation of the object feature point image under time delay is based on a proposed robust decorrelation Kalman filtering model, for the measurement vectors which cannot be obtained during time delay in the robust Kalman filtering model, a polynomial fitting method is proposed in which the selection of the polynomial includes the position, velocity and acceleration of the object feature point which impact the feature point trajectory, then the more accurate object feature point image can be obtained. From the estimated object feature point image under time delay, the more accurate image Jacobian matrix under time delay can be obtained. Simulation and experimental results verify the feasibility and superiority of this paper method.

Despite the significance of assortativity as a property of networks that paves for the emergence of new structural types, surprisingly, there has been little research done on assortativity. Assortative networks are perhaps among the most prominent examples of complex networks believed to be governed by common phenomena, thereby producing structures far from random. Further, certain vertices possess high centrality and can be regarded as significant and influential vertices that can become cluster centers that connect with high membership to many of the surrounding vertices. We propose a fuzzy clustering method to meaningfully characterize assortative, as well as disassortative, networks by adapting the Bonacichi’s power centrality to seek the high degree centrality vertices to become cluster centers. Moreover, we leverage our novel modularity function to determine the optimal number of clusters, as well as the optimal membership among clusters. However, due to the difficulty of finding real-world assortative network datasets that come with ground truths, we evaluated our method using synthetic data but possibly bearing resemblance to real-world network datasets as they were generated by the Lancichinetti–Fortunato–Radicchi benchmark. Our results show our non-hierarchical method outperforms a known hierarchical fuzzy clustering method, and also performs better than a well-known membership-based modularity function. Our method proved to perform beyond satisfactory for both assortative and disassortative networks.

In crowdsensing, the diversity of the sensing tasks and an enhancement of the smart devices enable mobile users to accept multiple types of tasks simultaneously. In this study, we propose a new practical framework for dealing with the challenges of task assignment and user incentives posed by complex heterogeneous task scenarios in a crowdsensing market full of competition. First, based on the non-cooperative game property of mobile users, the problem is formulated into a Nash equilibrium problem. Then, to provide an efficient solution, a judgment method based on constraints (sensing time and sensing task dimension) is designed to decompose the problems into different situations according to the complexity. We propose a genetic-algorithm-based approach to find the combination of tasks that maximizes the utility of users and adopts a co-evolutionary model to formulate a stable sensing strategy that maintains the maximum utility of all users. Furthermore, we reveal the impact of competition between users and tasks on user strategies and use a cooperative weight to reflect it mathematically. Based on this, an infeasible solution repair method is designed in the genetic algorithm to reduce the search space, thus effectively accelerating the convergence speed. Extensive simulations demonstrate the effectiveness of the proposed method.

Hierarchical topological structure learning methods are expected to be developed in the field of data mining for extracting multiscale topological structures from an unknown dataset. However, most methods require user-defined parameters, and it is difficult for users to determine these parameters and effectively utilize the method. In this paper, we propose a new parameter-less hierarchical topological structure learning method based on growing neural gas (GNG). First, we propose batch learning GNG (BL-GNG) to improve the learning convergence and reduce the user-designed parameters in GNG. BL-GNG uses an objective function based on fuzzy C-means to improve the learning convergence. Next, we propose multilayer BL-GNG (MBL-GNG), which is a parameter-less unsupervised learning algorithm based on hierarchical topological structure learning. In MBL-GNG, the input data of each layer uses parent nodes to learn more abstract topological structures from the dataset. Furthermore, MBL-GNG can automatically determine the number of nodes and layers according to the data distribution. Finally, we conducted several experiments to evaluate our proposed method by comparing it with other hierarchical approaches and discuss the effectiveness of our proposed method.

In this study, we formulate bimatrix games with fuzzy random payoffs, and introduce equilibrium solution concepts based on possibility and necessity measures. It is assumed that each player has linear fuzzy goals for his/her payoff. To obtain equilibrium solutions based on the possibility and necessity measures, we propose two algorithms in which quadratic programming problems are solved repeatedly until equilibrium conditions are satisfied.

This study provides an insight into the asymptotic stability of a drilling inclination system with a time-varying delay. An appropriate Lyapunov–Krasovskii functional (LKF) is essential for the stability analysis of the abovementioned system. In general, an LKF is constructed with each coefficient matrix being positive definite, which results in considerable conservatism. Herein, to relax the conditions of the derived criteria, a novel LKF is proposed by avoiding the positive-definite restriction of some coefficient matrices and introducing additional free matrices simultaneously. Subsequently, this relaxed LKF is applied to derive a less conservative stability criterion for the abovementioned system. Finally, the effect of reducing the conservatism of the proposed LKF is verified based on two examples.