基于金属织物和自然摩擦带电的电子皮肤对人体运动的智能识别  

Intelligent recognition of human motion using an ingenious electronic skin based on metal fabric and natural triboelectrification

作　　者：徐锦杰 陈婉翟 刘樑杰 江姗姗 王浩楠 张家翔 甘昕艳 周雄图 郭太良 吴朝兴 张永爱 Jinjie Xu;Wandi Chen;Liangjie Liu;Shanshan Jiang;Haonan Wang;Jiaxiang Zhang;Xinyan Gan;Xiongtu Zhou;Tailiang Guo;Chaoxing Wu;Yongai Zhang(College of Physics and Information Engineering,Fuzhou University,Fuzhou 350108,China;Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China,Fuzhou 350108,China)

机构地区：[1]College of Physics and Information Engineering,Fuzhou University,Fuzhou 350108,China [2]Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China,Fuzhou 350108,China

出　　处：《Science China Materials》2024年第3期887-897,共11页中国科学（材料科学）（英文版）

基　　金：supported by Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China(2021ZZ130);the Natural Science Foundation of Fujian Province,China(2021J01577)。

摘　　要：目前已开发出各种基于电子或光学信号的技术来感知身体运动,这在医疗保健、康复和人机交互等领域至关重要.然而,这些信号都是从身体外部获取的.本研究中,我们制备了一种电子皮肤(e-skin)人体运动传感器,它利用有机聚合物和金属织物的组合,通过人体的自然电荷感应(EI)来检测运动.该电子皮肤可获得高达450 V的人体电势信号.此外,该信号可通过最先进的深度学习技术自动提取和训练.该传感器能准确识别睡眠活动,准确率约为96.55%.这种可穿戴运动传感器可以与物联网技术无缝集成,实现多功能应用,展示了其在人类活动识别和人工智能方面的潜在用途.Various techniques based on electronic or optical signals have been developed to perceive body movements,which is essential in several fields such as healthcare, rehabilitation, and human-computer interaction. However,these signals are obtained externally, not from within the body. In this study, we introduce an electronic skin(e-skin)body motion sensor prepared using organic polymers and metal fabric to detect motion through the body's electro-induction(EI) via contact with the ground and shoes or through intrinsic contact electrification of the skin. The device can achieve an EI signal up to 450 V and charge data of 40 V and2.45 μA when it is detached from the contacted skin. Moreover, the signal can be automatically extracted and trained using the state-of-the-art deep learning techniques. The sensor can accurately track sleep activity with an accuracy rate of96.55%. This wearable motion sensor can be seamlessly combined with the Internet of Things technology for multifunctional applications, highlighting its potential applications in human activity recognition and artificial intelligence.

关 键 词：human activity recognition e-skin sleep motion recognition contact-separation electrification 1D-CNN 

分 类 号：TS106[轻工技术与工程—纺织工程] TP212[轻工技术与工程—纺织科学与工程]