Machine learning-assisted novel recyclable flexible triboelectric nanogenerators for intelligent motion

TENG-Boosted Smart Sports with Energy Autonomy and Digital Intelligence

Technological advancements have profoundly transformed the sports domain, ushering it into the digital era. Services leveraging big data in intelligent sports-encompassing performance analytics, training statistical evaluations and metrics-have become indispensable. These tools are vital in aiding athletes with their daily training regimens and in devising sophisticated competition strategies, proving crucial in the pursuit of victory. Despite their potential, wearable electronic devices used for motion monitoring are subject to several limitations, including prohibitive cost, extensive energy usage, incompatibility with individual spatial structures, and flawed data analysis methodologies. Triboelectric nanogenerators (TENGs) have become instrumental in the development of self-powered devices/systems owing to their remarkable capacity to harnessing ambient high-entropy energy from the environment. This paper provides a thorough review of the advancements and emerging trends in TENG-based intelligent sports, focusing on physiological data monitoring, sports training performance, event refereeing assistance, and sports injury prevention and rehabilitation. Excluding the potential influence of sports psychological factors, this review provides a detailed discourse on present challenges and prospects for boosting smart sports with energy autonomy and digital intelligence. This study presents innovative insights and motivations for propelling the evolution of intelligent sports toward a more sustainable and efficient future for humanity.

AI-Driven TENGs for Self-Powered Smart Sensors and Intelligent Devices

Triboelectric nanogenerators (TENGs) are emerging as transformative technologies for sustainable energy harvesting and precision sensing, offering eco-friendly power generation from mechanical motion. They harness mechanical energy while enabling self-sustaining sensing for self-powered devices. However, challenges such as material optimization, fabrication techniques, design strategies, and output stability must be addressed to fully realize their practical potential. Artificial intelligence (AI), with its capabilities in advanced data analysis, pattern recognition, and adaptive responses, is revolutionizing fields like healthcare, industrial automation, and smart infrastructure. When integrated with TENGs, AI can overcome current limitations by enhancing output, stability, and adaptability. This review explores the synergistic potential of AI-driven TENG systems, from optimizing materials and fabrication to embedding machine learning and deep learning algorithms for intelligent real-time sensing. These advancements enable improved energy harvesting, predictive maintenance, and dynamic performance optimization, making TENGs more practical across industries. The review also identifies key challenges and future research directions, including the development of low-power AI algorithms, sustainable materials, hybrid energy systems, and robust security protocols for AI-enhanced TENG solutions.

Self-Powered, Flexible, Wireless and Intelligent Human Health Management System Based on Natural Recyclable Materials

Combining wearable sensors with modern technologies such as internet of things and big data to monitor or intervene in obesity-induced chronic diseases, such as obstructive sleep apnea, type II diabetes, cardiovascular diseases, and Alzheimer's disease, is of great significance to the self-health management of human beings. This study designed a loofah-conducting graphite four friction layer enhanced triboelectric nanogenerator (LG-TENG) and developed a health management system for human motion recognition and early warning of sleep breathing abnormalities. By uniformly spraying and depositing conductive graphite on the surface of the loofah and the elastic film cross-interlocking bending structure design, the signal strength of the LG-TENG has been improved by 390%. The stable output signal is still maintained after 1500 s of continuous operation at a frequency of 2 Hz. LG-TENG can realize accurate motion analysis by muscle contraction state. Combining different deep learning models resulted in 98.1% accuracy in recognizing seven categories of displacement speeds for an individual and 96.46% accuracy in recognizing seven categories of displacement speeds for three individuals. In addition, the sleep breathing monitoring early warning system was developed by integrating Bluetooth wireless transmission and upper computer analysis technology. This system aims to analyze and provide real-time warnings for sleep-breathing abnormalities. This research promotes an innovation of TENG technology based on the advantages of natural materials, recyclability and low cost. It offers new ideas for self-health management and scientific exercise for obese people, showing a broad application prospect.

Leather-Based Shoe Soles for Real-Time Gait Recognition and Automatic Remote Assistance Using Machine Learning

Real-time monitoring of gait characteristics is crucial for applications in health monitoring, patient rehabilitation feedback, and telemedicine. However, the effective and stable acquisition and automatic analysis of gait information remain significant challenges. In this study, we present a flexible sensor based on a carbon nanotube/graphene composite conductive leather (CGL), which uses collagen fiber with a three-dimensional network structure as the flexible substrate. The CGL-based sensor demonstrates a high dynamic range, with notable pressure responses ranging from 0.6 to 14.5 kPa and high sensitivity (S = 0.2465 kPa-1). We further developed a device incorporating the CGL-based sensor to collect foot characteristic signals from human motion and designed smart sports shoes to facilitate effective human-computer interaction. Machine learning was employed to collect and process gait characteristic information in various states, including standing, sitting, walking, and falling. For real-time monitoring of falls, we optimized the K-Nearest Time Series Classifier (KNTC) algorithm, achieving an accuracy of 0.99 and a prediction time of only 13 ms, which highlights the system's excellent intelligent response capabilities. The system maintained a gait recognition accuracy of 90% across diverse populations, with low false-positive (3.3%) and false-negative (3.3%) rates. This work demonstrates stable gait recognition capabilities and provides valuable methods and insights for plantar behavior monitoring and data analysis, contributing to the development of advanced real-time gait monitoring systems.