Mobility support robots can be made available for use by patients in hospital settings. To prevent the robot from being used by unauthorized patients, an identification system must be installed on the robot. The FaceNet system is unable to recognize users when the camera is positioned to view from below, and the true recognition rate is lower when the threshold is set to a higher level. To address these issues, this paper proposes an adaptive face recognition system with a higher threshold setting and the capacity to adapt to bottom camera viewing angles. To achieve high threshold settings, this paper proposes a novel training strategy that enlarges the output distribution range through Negative Feature Augmentation (NFA) when training a Siamese network. The objective of NFA is to introduce additional negative sample pairs during the training phase, thereby enabling the network to expand the recognition distribution range. This hypothesis is demonstrated on the MNIST dataset. Furthermore, the proposed method was tested on the LFW benchmark dataset, resulting in an improved recognition rate of 0.86 when the threshold was set to 0.8. Subsequently, in order to achieve the ability to adaptively recognize users from bottom perspectives, we introduce the use of Growing Neural Gas (GNG) to track feature changes when the user faces different directions while using the robot. Furthermore, we propose methodologies for aligning eyes and standardizing faces, thereby ensuring that the input face is aligned with the learned features. In our experiments, we collected RGB videos of 16 college students using RT-1, and the results demonstrated a high accuracy rate of 0.80, outperforming other methods.

This paper deals with a privacy-preserving human tracking system that uses multi-property infrared sensor arrays. In the growing field of intelligent elderly care, there is a critical need for monitoring systems that ensure safety without compromising personal privacy. While traditional camera-based systems offer detailed activity recognition, privacy-related concerns often limit their practical application and user acceptance. Consequently, approaches that protect privacy at the sensor level have gained increasing attention. The privacy-preserving human tracking system proposed in this paper protects privacy at the sensor level by fusing data from an ultra-low-resolution $8\times 8$ (64-pixel) passive thermal infrared (IR) sensor array and a similarly low-resolution $8\times 8$ active Time-of-Flight (ToF) sensor. The thermal sensor identifies human presence based on heat signature, while the ToF sensor provides a depth map of the environment. By integrating these complementary modalities through a convolutional neural network (CNN) enhanced with a cross-attention mechanism, our system achieves real-time three-dimensional human tracking. Compared to previous methods using ultra-low-resolution IR sensors, which mostly only obtained two-dimensional coordinates, the acquisition of the Z coordinate enables the system to analyze changes in a person’s vertical position. This allows for the detection and differentiation of critical events such as falls, sitting, and lying down, which are ambiguous to 2D systems. With a demonstrated mean absolute error (MAE) of 0.172 m in indoor tracking, our system provides the data required for privacy-preserving Ambient Assisted Living (AAL) applications.

Developing flexible, cost-effective, and durable sensors is a key challenge for integrating Cyber–Physical–Human Systems (CPHSs) into smart homes. This paper introduces a flexible pressure sensor array designed for CPHS applications, addressing the need for cost-effective and durable sensors in smart homes. Our approach combines flexible piezoelectric materials with Swept Frequency Capacitive Sensing (SFCS). Unlike previous pressure sensors made of flexible piezoelectric materials, which can only measure dynamic pressure due to charge leakage, by using SFCS, the piezoelectric material is not directly in the circuit, and our sensor can effectively measure static pressure. While traditional arrays require multiple I/O ports or a matrix configuration, our design measures four distinct locations using only a single I/O port. The sensor is also mechanically flexible and exhibits high durability, capable of functioning even after being cut or torn, provided the electrode contact area remains largely intact. To decode the complex, multiplexed signal from this single channel, we developed a two-stage deep learning pipeline. We utilized data from thin-film resistive pressure sensors as ground truth. A classification model determines which of the four sensors are being touched. Then a regression model uses this touch-state information to estimate the corresponding pressure values. This pipeline employs a hybrid architecture that integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The results show that the system can estimate pressure values at each location. To demonstrate its application, the sensor system was integrated into a power recliner, thereby transforming the chair into an interactive tool for daily exercise designed to improve the well-being of older adults. This successful implementation establishes a viable pathway for the development of intelligent, interactive furniture for in-home exercise and rehabilitation within the CPHS paradigm.

Background: Ankle mobility and control contribute to balance and everyday movement throughout adulthood, yet are usually assessed through repetitive, abstract tasks that reveal little about movement production. Serious games can make repeated tasks engaging, but most report only end point scores rather than continuous gameplay signals, and few establish system usability. Developing and evaluating such a system in healthy adults is a necessary first step. Objective: This study aimed to develop Balance Wood, a bilateral ankle-controlled serious game in which seated players tilt a device through ankle flexion-extension to control on-screen play, to describe the system and the signals it records, and to evaluate its usability, safety, and user experience in healthy adults. Methods: In this two-stage cross-sectional development and usability study, healthy adults without lower-limb injury or balance-affecting neurological or vestibular disorders completed single-session repeated-measures procedures. In stage 1, a total of 40 adults—20 older (mean age 73.0, SD 5.9 y; 10 women) and 20 younger (mean age 28.1, SD 3.2 y; 4 women) adults—completed 3 fixed-order difficulty levels in 1 session (exploratory signal analysis). In stage 2, a total of 18 younger adults (mean age 24.6, SD 3.9 y; 5 women) completed the levels in counterbalanced order. Usability was assessed with the System Usability Scale (0‐100); use impressions and consciously used body parts with Likert and open-ended items; and device tilt-angle accuracy against a digital goniometer. Results: The mean System Usability Scale score was 81.5 (SD 11.2; 95% CI 76.0‐87.1; Cronbach α=.74), above the benchmark of 68, indicating good perceived usability. Mean ratings were 2.11 (SD 1.32) for safety concern (95% CI 1.45‐2.77) and 1.67 (SD 1.03) for pain (95% CI 1.15‐2.18). Ankle use was highest at 4.94 (SD 0.24), exceeding knee 2.50 (SD 1.29), hip 2.00 (SD 1.24), and trunk 2.17 (SD 1.15) by Wilcoxon signed-rank tests ( P <.001). Device readings agreed closely with the goniometer, with a mean absolute error of 0.66°, an intraclass correlation coefficient of 0.999, and 95% limits of agreement of −0.68 to 1.70°. In stage 1, all measures were computable for the 40 participants, with typical amplitudes of 20.5° to 27.2° and stable speed in both groups. In stage 2, repeated-measures analyses (α=.05) did not detect statistically significant differences across difficulty conditions or presentation positions (all P >.13). Conclusions: In healthy adults, Balance Wood was usable, well-accepted, low-risk, and provided accurate device-level tilt measurement with predominantly ankle-based control while continuously recording gameplay signals. It is a low-cost, bilateral, ankle-specific control interface with continuous signal capture into 1 easy-to-use device. Its contribution is a reproducible, usability-tested platform with characterized device accuracy, and formally defined candidate measures awaiting validation. Once validated, it could support home- or community-based recording; in the near term, it is a research tool.