Robustness-enhanced Myoelectric Control with GAN-based Open-set Recognition

TL;DR

This paper introduces a GAN-based open-set recognition framework to improve the robustness of myoelectric control systems, effectively handling unknown actions and reducing errors in EMG-based human motion recognition.

Contribution

It presents a novel GAN-based discriminator for open-set recognition in myoelectric control, enhancing system stability and accuracy in the presence of unknown actions.

Findings

Recognition accuracy of 97.6% for known actions

23.6% improvement in Active Error Rate (AER)

Efficient for deployment on edge devices

Abstract

Electromyography (EMG) signals are widely used in human motion recognition and medical rehabilitation, yet their variability and susceptibility to noise significantly limit the reliability of myoelectric control systems. Existing recognition algorithms often fail to handle unfamiliar actions effectively, leading to system instability and errors. This paper proposes a novel framework based on Generative Adversarial Networks (GANs) to enhance the robustness and usability of myoelectric control systems by enabling open-set recognition. The method incorporates a GAN-based discriminator to identify and reject unknown actions, maintaining system stability by preventing misclassifications. Experimental evaluations on publicly available and self-collected datasets demonstrate a recognition accuracy of 97.6\% for known actions and a 23.6\% improvement in Active Error Rate (AER) after rejecting unknown actions. The proposed approach is computationally efficient and suitable for deployment on edge devices, making it practical for real-world applications.