Elbeshbeshy Ahmed M, Rushdi Muhammad A, El-Metwally Shereen M
Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:661-664. doi: 10.1109/EMBC46164.2021.9630815.
Analysis and classification of electromyography (EMG) signals are crucial for rehabilitation and motor control. This study investigates electromyogram (EMG) time-frequency representations and then creates conventional and deep learning models for EMG signal classification. Firstly, a dataset of single-channel surface EMG signals has been recorded for four subjects to differentiate between forearm flexion and extension. Then, different time-frequency EMG representations have been used to build conventional and deep learning models for EMG classification. We compared the performance of pre-trained convolutional neural network models, namely GoogLeNet, SqueezeNet and AlexNet, and achieved accuracies of 92.71%, 90.63% and 87.5%, respectively. Also, data augmentation techniques on the levels of raw EMG signals and their time- frequency representations helped improve the accuracy of GoogLeNet to 96.88%. Furthermore, our approach demonstrated superior performance on another publicly available 10-class EMG dataset, and also using traditional classifiers trained on hand-crafted features.
肌电图（EMG）信号的分析与分类对于康复和运动控制至关重要。本研究调查了肌电图（EMG）的时频表示，然后创建了用于EMG信号分类的传统模型和深度学习模型。首先，记录了四个受试者的单通道表面肌电信号数据集，以区分前臂的屈伸。然后，使用不同的时频EMG表示来构建用于EMG分类的传统模型和深度学习模型。我们比较了预训练卷积神经网络模型（即GoogLeNet、SqueezeNet和AlexNet）的性能，分别达到了92.71%、90.63%和87.5%的准确率。此外，在原始EMG信号及其时频表示层面上的数据增强技术有助于将GoogLeNet的准确率提高到96.88%。此外，我们的方法在另一个公开可用的10类EMG数据集上表现出卓越性能，并且在使用基于手工特征训练的传统分类器时也是如此。
