K Divya Bharathi, P A Karthick, S Ramakrishnan
Non-Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India.
Physiological Measurements and Instrumentation Laboratory, Department of Instrumentation and Control Engineering, National Institute of Technology Tiruchirappalli, Tiruchirappalli, India.
Comput Methods Biomech Biomed Engin. 2022 Feb;25(3):320-332. doi: 10.1080/10255842.2021.1955104. Epub 2021 Jul 22.
In this study, an attempt has been made to develop an automated muscle fatigue detection system using cyclostationary based geometric features of surface electromyography (sEMG) signals. For this purpose, signals are acquired from fifty-eight healthy volunteers under dynamic muscle fatiguing contractions. The sEMG signals are preprocessed and the epochs of signals under nonfatigue and fatigue conditions are considered for the analysis. A computationally effective Fast Fourier transform based accumulation algorithm is adapted to compute the spectral correlation density coefficients. The boundary of spectral density coefficients in the complex plane is obtained using alpha shape method. The geometric features, namely, perimeter, area, circularity, bending energy, eccentricity and inertia are extracted from the shape and the machine learning models based on multilayer perceptron (MLP) and extreme learning machine (ELM) are developed using these biomarkers. The results show that the cyclostationarity increases in fatigue condition. All the extracted features are found to have significant difference in the two conditions. It is found that the ELM model based on prominent features classifies the sEMG signals with a maximum accuracy of 94.09% and F-score of 93.75%. Therefore, the proposed approach appears to be useful for analysing the fatiguing contractions in neuromuscular conditions.
在本研究中，已尝试利用基于循环平稳性的表面肌电图（sEMG）信号几何特征开发一种自动肌肉疲劳检测系统。为此，从58名健康志愿者在动态肌肉疲劳收缩状态下采集信号。对sEMG信号进行预处理，并考虑非疲劳和疲劳条件下的信号片段进行分析。采用一种计算效率高的基于快速傅里叶变换的累积算法来计算谱相关密度系数。使用α形状法获得复平面中谱密度系数的边界。从该形状中提取周长、面积、圆形度、弯曲能量、偏心率和惯性等几何特征，并利用这些生物标志物开发基于多层感知器（MLP）和极限学习机（ELM）的机器学习模型。结果表明，在疲劳状态下循环平稳性增加。发现所有提取的特征在两种状态下都有显著差异。发现基于突出特征的ELM模型对sEMG信号进行分类的最大准确率为94.09%，F值为93.75%。因此，所提出的方法似乎对分析神经肌肉疾病中的疲劳收缩有用。
