Research on sEMG Feature Generation and Classification Performance Based on EBGAN

Abstract

Surface electromyography signal (sEMG) recognition technology requires a large number of samples to ensure the accuracy of the training results. However, sEMG signals generally have the problems of a small amount of data, complicated acquisition process and large environmental influence, which hinders the improvement of the accuracy of sEMG classification. In order to improve the accuracy of sEMG classification, an sEMG feature generation method based on an energy generative adversarial network (EBGAN) is proposed in this paper for the first time. The energy concept is introduced into the discriminant network instead of the traditional binary judgment, and the distribution of the real EMG dataset is learned and captured by multiple fully connected layers, with similar sEMG data being generated. The experimental results show that, compared with other types of GAN networks, this method achieves a small maximum mean discrepancy in comparison with that of the original data. The experimental results using different typical classification models show that the data augmentation method proposed can effectively improve the classification accuracy of typical classification models, and the accuracy increase range is 1~5%.

Synthesis of sEMG Signals for Hand Gestures Using a 1DDCGAN

“…Zhang et al [8] used one-dimensional energy-based generative adversarial networks (EBGAN) to generate sEMG features to improve classification precision. The discriminant network uses the energy paradigm instead of binary assessment, and the fully linked layers capture the distribution of genuine sEMG data to create comparable data.…”

“…Nevertheless, these datasets might have missing or damaged data [6] or lack the gesture repetitions needed to build a robust classification model, resulting in overfitting, according to Kaczmarek et al [7]. Some researchers represented the sEMG signal in two dimensions and employed translation and rotation to augment the data, but these methods are not appropriate for one-dimensional time series data [8].…”

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

“…LSTMs were trained within MATLAB, using the Adam optimizer because of its computational efficiency and its success in non-stationary data (Kingma and Ba, 2015). Trainings were stopped after 200 epochs (e.g., Zhang and Ma, 2023). The selection of the number of hidden units for joint position and moment predictor LSTMs was based on previous studies aiming at utilization of sEMG in joint kinetics and kinematics predictions (Kim et al, 2020;Bao et al, 2021), such that a range of 250 units was chosen for both.…”