PatchEMG: Few-Shot EMG Signal Generation With Diffusion Models for Data Augmentation to Improve Classification Performance

Abstract

Electromyography (EMG) signals find wide applications in the fields of medicine, sports, and rehabilitation. However, the collection of EMG signals is a laborious process constrained by ethical limitations, resulting in a scarcity of available data and limiting its applicability in various tasks. This study aims to address this limitation by employing generative techniques to synthesize high-quality and diverse EMG signal samples and to evaluate their classification accuracy through gesture recognition tasks. We propose an improved approach based on diffusion probabilistic models, specifically tailored to the characteristics of EMG signals and the requirements of low-data setting. Our approach employs a conditional generative method, leveraging diffusion models and introducing a patch-based training strategy. Additionally, we have improved the network architecture of denoising diffusion probabilistic models (DDPM) to better suit the task of few-shot EMG signals generation. We evaluate the performance of the generated EMG signals in gesture recognition tasks using the Ninapro DB4, DB5, BioPatRec DB2, and DB3 datasets. The results indicate that when using 20% of the available data for training and generating the same amount of synthetic samples, the average classification accuracy of the generated data reached 94.31% of that of the real data. These findings demonstrate the effectiveness of our approach in modeling the distribution of real data and generating usable synthetic data. Moreover, the addition of synthetic data to the training set significantly enhances classification performance, further validating the efficacy of the generated data. Our proposed approach based on diffusion models exhibits promising performance in few-shot EMG signal generation task. This research contributes to the field of EMG signal synthesis and offers new possibilities for data augmentation, enabling more robust and accurate analysis of EMG signals in various applications.