The use of humanoid robots within a therapeutic role, that is, helping individuals with social disorders, is an emerging field, but it remains unexplored in terms of concentration training. To seamlessly integrate humanoid robots into concentration games, an investigation into the impacts of human robot interactive proxemics on concentration-training games is particularly important. In the case of an epidemic diffusion especially—for example, during the COVID-19 pandemic—HRI games may help in the therapeutic phase, significantly reducing the risk of contagion. In this paper, concentration games were designed by action imitation involving 120 participants to verify the hypothesis. Action-imitation accuracy, the assessment of emotional expression, and a questionnaire were compared with analysis of variance (ANOVA). Experimental results showed that a 2 m distance and left-front orientation for a human and a robot are optimal for human robot interactive concentration training. In addition, females worked better than males did in HRI imitation games. This work supports some valuable suggestions for the development of HRI concentration-training technology, involving the designs of friendlier and more useful robots, and HRI game scenarios.

In order to alleviate bottlenecks such as the lack of professional teachers, inattention during training processes, and low effectiveness in concentration training, we have proposed an immersive human–robot interactive (HRI) game framework based on deep learning for children’s concentration training and demonstrated its use through human–robot interactive games based on gesture recognition. The HRI game framework includes four functional modules: video data acquisition, image recognition modeling, a deep learning algorithm (YOLOv5), and information feedback. First, we built a gesture recognition model containing 10,000 pictures of children’s gestures, using the YOLOv5 algorithm. The average accuracy in recognition trainingwas 98.7%. Second, we recruited 120 children with attention deficits (aged from 9 to 12 years) to play the HRI games, including 60 girls and 60 boys. In the HRI game experiment, we obtained 8640 sample data, which were normalized and processed.According to the results, we found that the girls had better visual short-term memory and a shorter response time than boys. The research results showed that HRI games had a high efficacy, convenience, and full freedom, making them appropriate for children’s concentration training.

The construction of a similarity matrix is one significant step for the spectral clustering algorithm; while the Gaussian kernel function is one of the most common measures for constructing the similarity matrix. However, with a fixed scaling parameter, the similarity between two data points is not adaptive and appropriate for multi-scale datasets. In this paper, through quantitating the value of the importance for each vertex of the similarity graph, the Gaussian kernel function is scaled, and an adaptive Gaussian kernel similarity measure is proposed. Then, an adaptive spectral clustering algorithm is gotten based on the importance of shared nearest neighbors. The idea is that the greater the importance of the shared neighbors between two vertexes, the more possible it is that these two vertexes belong to the same cluster; and the importance value of the shared neighbors is obtained with an iterative method, which considers both the local structural information and the distance similarity information, so as to improve the algorithm’s performance. Experimental results on different datasets show that our spectral clustering algorithm outperforms the other spectral clustering algorithms, such as the self-tuning spectral clustering and the adaptive spectral clustering based on shared nearest neighbors in clustering accuracy on most datasets.

This paper focuses on the problem of intelligent evacuation route planning for emergencies, including natural and human resource disasters and epidemic disasters, such as the COVID-19 pandemic. The goal of this study was to quickly generate an evacuation route for a community for victims to be evacuated to safe areas as soon as possible. The evacuation route planning problem needs to determine appropriate routes and allocate a specific number of victims to each route. This paper formulates the problem as a maximum flow problem and proposes a binary search algorithm based on a maximum flow algorithm, which is an intelligent optimization evacuation route planning algorithm for the community. Furthermore, the formulation is a nonlinear optimization problem because each route’s suggested evacuation time is a convex nonlinear function of the number of victims assigned to that route. Finally, numerical examples and Matlab simulations demonstrate not only the algorithm’s effectiveness, but also that the algorithm has low complexity and high precision. The study’s findings offer a practical solution for nonlinear models of evacuation route planning, which will be widely used in human society and robot path planning schemes.

This article proposes an interleaved soft-switching converter with high voltage conversion ratio as an alternative to existing hard-switching converters, such that the switching loss can be reduced. This proposed soft-switching converter not merely boosts the output voltage of a fuel cell to a high level, that is applied to a high voltage DC link or a DC load, but also reduces the current stress in main switches, the input current and the output voltage ripples. A resonant auxiliary branch is connected in parallel with either main switch employed in a conventional hard-switching converter, such that the voltage drop across the main switch falls to zero before the main switch is triggered. In doing so, the aim of zero voltage switching (ZVS) is achieved, leading to a reduced switching loss, promoted conversion efficiency and lowered switching stress. In the end, this work is applied to fuel cells and validated by a good agreement between simulations and experiments.