Cyber-physical-social systems (CPSS) are expected to support telemedicine and will be the future of independent rehabilitation. However, a connection between the physical and cognitive as one of the social aspects has not been adequately supported. This paper proposes a multiscopic CPSS framework to investigate this issue by developing hand–object interaction (HOI) recognition with visual attention for the block-design test (BDT). We use three vision systems to extract hand features from block interaction. First, a hand-tracking vision is used to collect the hand-skeletal data and finger joint angle feature. We estimate the physical handling postures at the microscopic level. Second, an egocentric vision with an eye tracker is used to get hand and eye movement at the mesoscopic level. We analyze hand-eye coordination through hand gestures and the focus of visual attention when the hand interacts with the block. Third, an evaluation vision is used to classify the color features in each block at the macroscopic level. The system can recognize whether the design matches the task given. The eight-block design test with two scenarios demonstrates that the system can successfully measure human behavior from physical to cognitive during BDT. We investigate the relationship between physical and cognitive evaluation through the experiment in eight healthy persons. The regression and correlation analyses between the dominant and non-dominant hands show that evaluation indices – skewness-kurtosis of handling posture, attention to pattern, and attention to blocks – could indicate improvement during BDT. We believe this study will benefit clinicians and researchers by providing information unavailable in clinical settings. Code and datasets are available online at https://github.com/anom-tmu/bdt-multiscopic.

Growing neural gas (GNG) has been widely used in topological mapping, clustering and unsupervised tasks. It starts from two random nodes and grows until it forms a topological network covering all data. The time required for growth depends on the total amount of data and the current network nodes. To accelerate growth, we introduce a novel distributed batch processing method to extract the rough distribution called Distributed Batch Learning Growing Neural Gas (DBL-GNG). First, instead of using a for loop in standard GNG, we adopt a batch learning approach to accelerate learning. To do this, we replace most of the standard equations with matrix calculations. Next, instead of starting with two random nodes, we start with multiple nodes in different distribution areas. Furthermore, we also propose to add multiple nodes to the network instead of adding them one by one. Finally, we introduce an edge cutting method to reduce unimportant links between nodes to obtain a better cluster network. We demonstrate DBL-GNG on multiple benchmark datasets. From the results, DBL-GNG performs faster than other GNG methods by at least 10 times. We also demonstrate the scalability of DBL-GNG by implementing a multi-scale batch learning process in it, named MS-DBL-GNG, which successfully obtains fast convergence results. In addition, we also demonstrate the dynamic data adaptation of DBL-GNG to 3D point cloud data. It is capable of processing and mapping topological nodes on point cloud objects in real time.

Understanding human comfort when in the presence of robots is vital to constructing socially adaptive robotic systems. This study introduces the Human–Robot Proxemic Index (HRPI). This quantitative model estimates user comfort based on three contextual dimensions: human activity (behavior-dependent, BD), interaction type (interaction-dependent, ID), and object characteristics (object-dependent, OD). Unlike previous proxemic models that focused solely on physical distance, HRPI integrates multidimensional contextual factors and applies sigmoid-based personalization to account for individual sensitivity. A ceiling-mounted service robot and nine participants took part in experiments. Pre- and post-interaction questionnaires were used to find out how comfortable the participants felt and what distance they preferred. The collected data were normalized and incorporated into HRPI through weighted assessment, and validation with ideal dummy data in trials showed that HRPI-based control dynamically adjusted the robot’s approach distance and speed according to user preferences. These findings highlight the strengths of HRPI as a multidimensional, context-aware framework for guiding socially appropriate robot movements and suggest that its integration with topological spatial mapping could further enhance human–robot collaboration in real-world environments.

This paper introduces an artificial intelligence (AI) interactive system featuring a self-growing memory network designed to enhance self-efficacy, reduce loneliness, and maintain social interaction among the elderly. The system dynamically analyzes and processes user-written diaries, generating empathic and personalized responses tailored to each individual. The system architecture includes an experience extraction model, a self-growing memory network that provides a contextual understanding of the user’s daily life, a chat agent, and a feedback loop that adaptively learns the user’s behavioral patterns and emotional states. By drawing on both successful and challenging experiences, the system crafts responses that reinforce the self-efficacy of the user, fostering a sense of accomplishment and engagement. This approach improves the psychological well-being of elderly users and promotes their mental health and overall quality of life through consistent interaction. To validate our proposed method, we developed a diary application to facilitate user interaction and collect diary entries. Over time, the system’s capacity to learn and adapt further refines the user experience, suggesting that AI-driven solutions hold significant potential for mitigating the effects of declining self-efficacy on mental health and social interactions. With the proposed system, we achieve an average system usability scale score of 77.3 (SD = 5.4) and a general self-efficacy scale score of 34.2 (SD = 3.5).

This paper presents a method of pose estimation with camera localization based on a genetic algorithm to derive the joint angle using an inverse kinematics model. In recent years, some open-source libraries for human skeleton tracking that can be implemented on smartphones have been released. Such software can detect joint positions of a skeleton from a 2D camera image; however, the 3D posture cannot be obtained. We therefore propose a method to estimate joint angles by using skeleton data. In the proposed approach, we use a multi-island genetic algorithm to maintain the diversity of the population and design a multi-objective function to improve the robustness. Moreover, structured learning based on topological mapping is implemented in the proposed method to enhance searching efficiency. In an experiment, the proposed method reduced the effect of outliers caused by misdetection. In addition, the structured learning was effective in decreasing the difference between skeleton data and the estimated poses.

Title: Unsupervised Anomaly Detection for IoT-Driven Multivariate Time Series on Moringa Leaf Extraction | Keywords: moringa leaf extraction, IoT, unsupervised anomaly detection, multivariate time series | Author: Kurnianingsih, Retno Widyowati, Achmad Fahrul Aji, Eri Sato-Shimokawara, Takenori Obo, and Naoyuki Kubota