Kumar Dinesh Kant, Pah Nemuel D, Bradley Alan
School of Electrical and Computing System Engineering, RMIT University, Melbourne 3000, Australia.
IEEE Trans Neural Syst Rehabil Eng. 2003 Dec;11(4):400-6. doi: 10.1109/TNSRE.2003.819901.
Muscle fatigue is often a result of unhealthy work practice. It has been known for some time that there is a significant change in the spectrum of the electromyography (EMG) of the muscle when it is fatigued. Due to the very complex nature of this signal however, it has been difficult to use this information to reliably automate the process of fatigue onset determination. If such a process implementation were feasible, it could be used as an indicator to reduce the chances of work-place injury. This research report on the effectiveness of the wavelet transform applied to the EMG signal as a means of identifying muscle fatigue. We report that with the appropriate choice of wavelet functions and scaling factors, it is possible to achieve reliable discrimination of the fatigue phenomenon, appropriate to an automated fatigue identification system.
肌肉疲劳通常是不健康工作方式的结果。人们早就知道，肌肉疲劳时其肌电图（EMG）频谱会发生显著变化。然而，由于该信号的性质非常复杂，很难利用这些信息可靠地自动确定疲劳起始过程。如果这样的过程实施可行，它可以作为一种指标来减少工作场所受伤的几率。本研究报告探讨了将小波变换应用于EMG信号作为识别肌肉疲劳手段的有效性。我们报告称，通过适当选择小波函数和缩放因子，可以实现对疲劳现象的可靠判别，适用于自动疲劳识别系统。
Zotero 插件