Suppr超能文献

使用柔性压阻式压力传感器通过握力对七个体育项目中的运动表现进行评估。

The assessment of sports performance by grip pressure using flexible piezoresistive pressure sensors in seven sports events.

作者信息

Zhang Kebao, Guo Beilei, Yang Mingchuan, Jia Yi, Zhang Kehu, Wang Liu

机构信息

School of Sport and Physical Education, North University of China, Taiyuan, 030051, China.

School of Recreation and Community Sport, Capital University of Physical Education and Sports, Beijing, 100191, China.

出版信息

Sci Rep. 2024 Dec 30;14(1):31750. doi: 10.1038/s41598-024-82274-1.

Abstract

Flexible micro-sensors have significant application potential in the field of sports performance evaluation. The aim of this study is to assess sports performance by grip pressure using a MMSS sensor (MXene as the sensitive material and melamine sponge as the substrate, a type of flexible piezoresistive pressure sensor). The grip pressures of expert and amateur players are evaluated in single skills events (golf, billiards, basketball, javelin and shot put) and in skills conversion (badminton and tennis). Indicators (time nodes, intervals, peaks, etc.) related to grip pressure on the handle are collected, analyzed, and identified by artificial intelligence. Finally, the K-Nearest Neighbor (KNN) of artificial intelligence algorithms is employed to identify differences for 400 strokes of tennis players in interval training session. Expert tennis athlete exhibits a higher level of precision, concentration and stability for exert and release of grip force (KNN accuracy of train 95.0%) than amateur (KNN: 84.6%) during single movement, technical conversion, and interval training condition. This research offers a new perspective for evaluating sports performance in hand-held equipment events and presents a feasible direction for facing challenges of flexible wearable technology in practice.

摘要

柔性微传感器在运动表现评估领域具有巨大的应用潜力。本研究旨在通过使用MMSS传感器(以MXene为敏感材料、三聚氰胺海绵为基底的一种柔性压阻式压力传感器)测量握力来评估运动表现。在单项技能项目(高尔夫、台球、篮球、标枪和铅球)以及技能转换项目(羽毛球和网球)中评估专业和业余运动员的握力。通过人工智能收集、分析和识别与手柄上握力相关的指标(时间节点、间隔、峰值等)。最后,采用人工智能算法中的K近邻(KNN)对网球运动员在间歇训练中的400次击球进行差异识别。在单一动作、技术转换和间歇训练条件下,专业网球运动员在握力施加和释放方面表现出比业余运动员更高的精准度、专注力和稳定性(训练的KNN准确率:专业运动员为95.0%,业余运动员为84.6%)。本研究为手持式装备项目中的运动表现评估提供了新视角,并为柔性可穿戴技术在实际应用中面临的挑战提出了可行方向。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b130/11686128/ebf72e1235da/41598_2024_82274_Fig1_HTML.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验