East China University of Technology, Nanchang, Jiangxi, China.
PLoS One. 2022 Dec 1;17(12):e0276921. doi: 10.1371/journal.pone.0276921. eCollection 2022.
Muscle fatigue is a crucial indicator to determine whether training is in place and to protect trainers.
To make full use of morphological information of surface EMG and ECG signals in the time domain, a new idea and method for the fatigue assessment of exercise muscles based on data fusion is proposed in this paper.
sEMG and ECG time series with the same length were obtained by signal preprocessing and sequence normalization, feature extraction of sequence tenses was realized by a deep learning network based on sequential convolution and signal fusion model of muscle fatigue evaluation was established by D-S evidence theory.
Thirty volunteers were recruited and divided into three groups. ECG signals and sEMG signals at the biceps brachii of the right upper limb were monitored in a 20-minute exercise cycle.
The prediction result of TCN based on time domain signal is better than the commonly used KNN and SVM recognition algorithm, and the recognition accuracy of relaxed, excessive and fatigue by D-S fusion was 89%, 86%, 88.5%. The accuracy was 0.9055, 0.9494 and 0.9269, respectively. The recall rates of the three conditions were 0.9303, 0.9570 and 0.9435. The F-score of the three conditions was 0.8911, 0.8764 and 0.8837, respectively.
Based on time series and time series convolutional network, sEMG and ECG fusion of motor muscle recognition method can better distinguish different state information and has certain practical value in the fields of muscle evaluation, clinical diagnosis, wearable devices and so on.
肌肉疲劳是判断训练是否到位和保护训练者的关键指标。
充分利用表面肌电和心电图信号的时域形态信息，提出一种基于数据融合的运动肌疲劳评估新思想和方法。
通过信号预处理和序列归一化，得到等长的 sEMG 和 ECG 时间序列，基于序列卷积的深度学习网络实现序列时态特征提取，建立肌肉疲劳评估的信号融合模型，基于 D-S 证据理论。
招募 30 名志愿者，分为三组。在 20 分钟的运动周期中，监测右上臂肱二头肌的 ECG 信号和 sEMG 信号。
基于时域信号的 TCN 预测结果优于常用的 KNN 和 SVM 识别算法，D-S 融合对放松、过度和疲劳的识别准确率分别为 89%、86%和 88.5%。准确率分别为 0.9055、0.9494 和 0.9269，召回率分别为 0.9303、0.9570 和 0.9435。F 分数分别为 0.8911、0.8764 和 0.8837。
基于时间序列和时间序列卷积网络，对运动肌 sEMG 和 ECG 融合的识别方法可以更好地区分不同的状态信息，在肌肉评估、临床诊断、可穿戴设备等领域具有一定的实用价值。
