Analysis of Contraction Effort Level in EMG-Based Gesture Recognition Using Hyperdimensional Computing

TL;DR

This paper presents a hyperdimensional computing approach to improve EMG-based gesture recognition by making it robust to muscle contraction effort variations, achieving significant accuracy recovery across effort levels.

Contribution

The study introduces a novel hyperdimensional computing method that enhances robustness and multi-level effort recognition in EMG gesture classification.

Findings

Up to 39.17% accuracy drop across effort levels without adaptation.

Up to 30.35% accuracy recovery with the proposed algorithm.

Effective recognition of multiple contraction levels in EMG gestures.

Abstract

Varying contraction levels of muscles is a big challenge in electromyography-based gesture recognition. Some use cases require the classifier to be robust against varying force changes, while others demand to distinguish between different effort levels of performing the same gesture. We use brain-inspired hyperdimensional computing paradigm to build classification models that are both robust to these variations and able to recognize multiple contraction levels. Experimental results on 5 subjects performing 9 gestures with 3 effort levels show up to 39.17% accuracy drop when training and testing across different effort levels, with up to 30.35% recovery after applying our algorithm.