Recently, Associate Professor Mao Yupeng’s micro-nano intelligent sports research team from the Physical Education Department of NEU has made breakthroughs in the field of biomass triboelectric sensing enabling sports health. The study titled Deep-learning-assisted Neck Motion Monitoring System Self-powered through Biodegradable Triboelectric Sensors was published in the internationally renowned journal Advanced Functional Materials (Q1, CAS, Impact Factor 19.2). Sun Fengxin, a postgraduate of 2021 from the Physical Education Department is the first author of the paper, Associate Professor Mao Yupeng is the corresponding author, and NEU is the first and corresponding unit.
In the new era of artificial intelligence and the Internet of Things, smart sports big data collection and analysis are of great significance to human health monitoring. Wearable electronics, integrating advanced sensors and data analysis algorithms, can analyze human health in real time and accurately track and record human activities, providing unprecedented opportunities for personalized health monitoring and exercise training. It should be pointed out that the traditional battery-powered devices have limited the application of wearable electronics in the field of motion monitoring. For instance, frequent battery replacement or charging and waste batteries will not only lead to environmental pollution, but also not be conducive to the real-time monitoring of the motion process. In this study, a kind of self-powered biodegradable triboelectric sensor is developed by using natural biodegradable biomass material - corn bracts as dielectric layer and the triboelectric nanopower generation technology. The study has avoided the environmental pollution caused by burning corn bracts, realized the collection of human mechanical energy, and achieved the intelligent monitoring of human motion.
To achieve neck stability monitoring during exercise and neck disease prevention during daily life, the research team integrated three identical NB-TENG sensors with stretchable textiles to obtain a wearable neck condition monitoring sensor (NCM-TS). By combining NCM-TS with a deep learning model, an intelligent behavior monitoring system was built. This system is able to identify four types of neck motions with an average accuracy of 94%. The neck motion monitoring sensor developed in this study has wide application potential in intelligent sports big data collection, motion monitoring, rehabilitation training and medical care.