Innovations related to textiles-based sensors have drawn great interest due to their outstanding merits of flexibility, comfort, low cost, and wearability. Textile-based sensors are often tied to certain parts of the human body to collect mechanical, physical, and chemical stimuli to identify and record human health and exercise. Until now, much research and review work has been carried out to summarize and promote the development of textile-based sensors. As a feature, we focus on textile-based mechanical sensors (TMSs), especially on their advantages and the way they achieve performance optimizations in this review. We first adopt a novel approach to introduce different kinds of TMSs by combining sensing mechanisms, textile structure, and novel fabricating strategies for implementing TMSs and focusing on critical performance criteria such as sensitivity, response range, response time, and stability. Next, we summarize their great advantages over other flexible sensors, and their potential applications in health monitoring, motion recognition, and human-machine interaction. Finally, we present the challenges and prospects to provide meaningful guidelines and directions for future research. The TMSs play an important role in promoting the development of the emerging Internet of Things, which can make health monitoring and everyday objects connect more smartly, conveniently, and comfortably efficiently in a wearable way in the coming years.

Accurate and real-time gesture recognition is required for the autonomous operation of prosthetic hand devices. This study employs a convolutional neural network-enhanced channel attention (CNN-ECA) model to provide a unique approach for surface electromyography (sEMG) gesture recognition. The introduction of the ECA module improves the model’s capacity to extract features and focus on critical information in the sEMG data, thus simultaneously equipping the sEMG-controlled prosthetic hand systems with the characteristics of accurate gesture detection and real-time control. Furthermore, we suggest a preprocessing strategy for extracting envelope signals that incorporates Butterworth low-pass filtering and the fast Hilbert transform (FHT), which can successfully reduce noise interference and capture essential physiological information. Finally, the majority voting window technique is adopted to enhance the prediction results, further improving the accuracy and stability of the model. Overall, our multi-layered convolutional neural network model, in conjunction with envelope signal extraction and attention mechanisms, offers a promising and innovative approach for real-time control systems in prosthetic hands, allowing for precise fine motor actions.

Flexible sensors have attracted extensive attention because of their promising applications in the fields of health monitoring, intelligent robots, and electronic skin, etc. During the COVID-19 epidemic, noncontact control of public equipment such as elevators, game consoles, and doors has become particularly important, as it can effectively reduce the risk of cross-infection. In this work, a noncontact flexible temperature sensor is prepared via a simple dip-drying progress, in which poly(3,4-ethylenedioxythiophene):poly(4-styrene sulfonate) (PEDOT:PSS) and printer paper served as the sensing material and the flexible substrate, respectively. We combined the highly sensitive temperature-responsive property of PEDOT:PSS with the good hygroscopicity of printer paper. The prepared sensor shows high sensitivity and good stability in noncontact sensing mode within the temperature range of 20–50 °C. To prove the practicability of the noncontact temperature sensor, a 3 × 2 sensing array is prepared as a noncontact human-machine interface to realize the interaction between player and “Pound-A-Mole game” and a Bluetooth car. These two demos show the sensor′s ability to perceive nearby temperature changes, verifying its application potential as a noncontact human-machine interaction interface.