Analysis of Contraction Effort Level in EMG-Based Gesture Recognition Using Hyperdimensional Computing
This work addresses the problem of improving robustness and specificity in electromyography-based gesture recognition for applications like prosthetics or human-computer interaction, representing an incremental advancement in handling effort-level variations.
The paper tackled the challenge of varying muscle contraction levels in EMG-based gesture recognition by using hyperdimensional computing to build models robust to these variations and capable of recognizing multiple effort levels. Experimental results on 5 subjects performing 9 gestures with 3 effort levels showed up to a 39.17% accuracy drop across different effort levels, with up to 30.35% recovery after applying their algorithm.
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.