Nowadays, wearable sensors play a vital role in the detection of human motions, innovating an alternate and intuitive form in human–computer interaction (HCI). In this study, we present a novel real-time wearable system for finger air-writing recognition in three-dimensional (3D) space based on the Arduino Nano 33 BLE Sense as an edge device, which can run TensorFlow Lite to realize recognition and classification on the device. This system enables users to have the freedom and flexibility to write characters (10 digits and 26 English lower-case letters) in free space by moving fingers and uses a deep learning algorithm to recognize 36 characters from the motion data captured by inertial measurement units (IMUs) and processed by a microcontroller, which are both embedded in an Arduino Nano 33 BLE Sense. We prepared 63000 air-writing stroke data samples of 35 subjects containing 18 males and 17 females for convolutional neural network (CNN) training and achieved a high recognition accuracy at 97.95%.

The demand for intelligent monitoring systems tailored to elderly living environments is rapidly increasing worldwide with population aging. Traditional acoustic scene monitoring systems that rely on cloud computing are limited by data transmission delays and privacy concerns. Hence, this study proposes an acoustic scene recognition system that integrates edge computing with deep learning to enable real-time monitoring of elderly individuals’ daily activities. The system consists of low-power edge devices equipped with multiple microphones, portable wearable components, and compact power modules, ensuring its seamless integration into the daily lives of the elderly. We developed four deep learning models—convolutional neural network, long short-term memory, bidirectional long short-term memory, and deep neural network—and used model quantization techniques to reduce the computational complexity and memory usage, thereby optimizing them to meet edge device constraints. The CNN model demonstrated superior performance compared to the other models, achieving 98.5% accuracy, an inference time of 2.4 ms, and low memory requirements (25.63 KB allocated for Flash and 5.15 KB for RAM). This architecture provides an efficient, reliable, and user-friendly solution for real-time acoustic scene monitoring in elderly care.

In recent years, advances in artificial intelligence, machine vision, and the Internet of Things have significantly impacted sports analytics, particularly basketball, where accurate measurement and analysis of player performance have become increasingly important. This study proposes a real-time goal state recognition system based on inertial measurement unit (IMU) sensors, focusing on four shooting scenarios: rebounds, swishes, other shots, and misses. By installing IMU sensors around the basketball net, the system captures real-time data on acceleration, angular velocity, and angular changes to comprehensively analyze the fluency and success rate of shooting execution, utilizing five deep learning models—convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), CNN-LSTM, and CNN-LSTM-Attention—to classify shot types. Experimental results indicate that the CNN-LSTM-Attention model outperformed other models with an accuracy of 87.79% in identifying goal states. This result represents a commanding level of real-time goal state recognition, demonstrating the robustness and efficiency of the model in complex sports environments. This high accuracy not only supports the application of the system in skill analysis and sports performance evaluation but also lays a solid foundation for the development of intelligent basketball training equipment, providing an efficient and practical solution for athletes and coaches.

This study proposes an edge computing-based facial expression recognition system that is low cost, low power, and privacy preserving. It utilizes a minimally obtrusive cap-based system designed for the continuous and real-time monitoring of a user’s facial expressions. The proposed method focuses on detecting facial skin deformations accompanying changes in facial expressions. A multi-zone time-of-flight (ToF) depth sensor VL53L5CX, featuring an 8 × 8 depth image, is integrated into the front brim of the cap to measure the distance between the sensor and the user’s facial skin surface. The distance values corresponding to seven universal facial expressions (neutral, happy, disgust, anger, surprise, fear, and sad) are transmitted to a low-power STM32F476 microcontroller (MCU) as an edge device for data preprocessing and facial expression classification tasks utilizing an on-device pre-trained deep learning model. Performance evaluation of the system is conducted through experiments utilizing data collected from 20 subjects. Four deep learning algorithms, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNN), are assessed. These algorithms demonstrate high accuracy, with CNN yielding the best result, achieving an accuracy of 89.20% at a frame rate of 15 frames per second (fps) and a maximum latency of 2 ms.

Human–computer interaction is demanded for natural and convenient approaches, in which finger-writing recognition has aroused more and more attention. In this paper, a device-free finger-writing character recognition system based on an array of time-of-flight (ToF) distance sensors is presented. The ToF sensors acquire distance values between sensors to a writing finger within a 9.5 × 15 cm square on a surface at specific time intervals and send distance data to a low-power microcontroller STM32F401, equipped with deep learning algorithms for real-time inference and recognition tasks. The proposed method enables one to distinguish 26 English lower-case letters by users writing with their fingers and does not require one to wear additional devices. All data used in this work were collected from 21 subjects (12 males and 9 females) to evaluate the proposed system in a real scenario. In this work, the performance of different deep learning algorithms, such as long short-term memory (LSTM), convolutional neural networks (CNNs) and bidirectional LSTM (BiLSTM), was evaluated. Thus, these algorithms provide high accuracy, where the best result is extracted from the LSTM, with 98.31% accuracy and 50 ms of maximum latency.

Heart rate (HR) and respiration rate (RR) play an important role in the study of complex behaviors and their physiological correlations in non-human primates (NHPs). However, collecting HR and RR information is often challenging, involving either invasive implants or tedious behavioral training, and there are currently few established simple and non-invasive techniques for HR and RR measurement in NHPs owing to their stress response or indocility. In this study, we employed a frequency-modulated continuous wave (FMCW) radar to design a novel contactless HR and RR monitoring system. The designed system can estimate HR and RR in real time by placing the FMCW radar on the cage and facing the chest of both awake and anesthetized macaques, the NHP investigated in this study. Experimental results show that the proposed method outperforms existing methods, with averaged absolute errors between the reference monitor and radar estimates of 0.77 beats per minute (bpm) and 1.29 respirations per minute (rpm) for HR and RR, respectively. In summary, we believe that the proposed non-invasive and contactless estimation method could be generalized as a HR and RR monitoring tool for NHPs. Furthermore, after modifying the radar signal-processing algorithms, it also shows promise for applications in other experimental animals for animal welfare, behavioral, neurological, and ethological research.