Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification

Abstract

The acquisition of bio-signal from the human body requires a strict experimental setup and ethical approvements, which leads to limited data for the training of classifiers in the era of big data. It will change the situation if synthetic data can be generated based on real data. This article proposes such a kind of multiple channel electromyography (EMG) data enhancement method using a deep convolutional generative adversarial network (DCGAN). The generation procedure is as follows: First, the multiple channels of EMG signals within sliding windows are converted to grayscale images through matrix transformation, normalization, and histogram equalization. Second, the grayscale images of each class are used to train DCGAN so that synthetic grayscale images of each class can be generated with the input of random noises. To evaluate whether the synthetic data own the similarity and diversity with the real data, the classification accuracy index is adopted in this article. A public EMG dataset (that is, ISR Myo-I) for hand motion recognition is used to prove the usability of the proposed method. The experimental results show that adding synthetic data to the training data has little effect on the classification performance, indicating the similarity between real data and synthetic data. Moreover, it is also noted that the average accuracy (five classes) is slightly increased by 1%–2% for support vector machine (SVM) and random forest (RF), respectively, with additional synthetic data for training. Although the improvement is not statistically significant, it implies that the generated data by DCGAN own its new characteristics, and it is possible to enrich the diversity of the training dataset. In addition, cross-validation analysis shows that the synthetic samples have large inter-class distance, reflected by higher cross-validation accuracy of pure synthetic sample classification. Furthermore, this article also demonstrates that histogram equalization can significantly improve the performance of EMG-based hand motion recognition.

A Physics-Informed Low-Shot Adversarial Learning for sEMG-Based Estimation of Muscle Force and Joint Kinematics

“…The GAN-based model is capable of discovering the structured patterns of the references and extrapolating the underlying data distribution characteristics during the adversarial learning process [34]. For example, Chen et al [35] tested and evaluated the performance of the deep convolutional generative adversarial network (DCGAN) on sEMG-based data enhancement, and their results indicated that the extrapolated data is able to augment the diversity of the original data. Fahimi et al [36] The continuous estimation of muscle forces (F ) and joint 153 kinematics(θ) from multi-channel sEMG can be denoted as 154 the time-series generation problem.…”