MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition

TL;DR

The paper introduces MoEMba, a novel Mamba-based mixture of experts framework utilizing Selective StateSpace Models and wavelet features to improve high-density EMG-based hand gesture recognition, addressing inter-session variability.

Contribution

It presents a new MoEMba framework that enhances gesture recognition accuracy by capturing temporal dependencies and cross-channel interactions with innovative attention and wavelet techniques.

Findings

Achieves 56.9% balanced accuracy on CapgMyo dataset.

Outperforms existing state-of-the-art methods.

Demonstrates robustness to session-to-session variability.

Abstract

High-Density surface Electromyography (HDsEMG) has emerged as a pivotal resource for Human-Computer Interaction (HCI), offering direct insights into muscle activities and motion intentions. However, a significant challenge in practical implementations of HD-sEMG-based models is the low accuracy of inter-session and inter-subject classification. Variability between sessions can reach up to 40% due to the inherent temporal variability of HD-sEMG signals. Targeting this challenge, the paper introduces the MoEMba framework, a novel approach leveraging Selective StateSpace Models (SSMs) to enhance HD-sEMG-based gesture recognition. The MoEMba framework captures temporal dependencies and cross-channel interactions through channel attention techniques. Furthermore, wavelet feature modulation is integrated to capture multi-scale temporal and spatial relations, improving signal representation. Experimental results on the CapgMyo HD-sEMG dataset demonstrate that MoEMba achieves a balanced accuracy of 56.9%, outperforming its state-of-the-art counterparts. The proposed framework's robustness to session-to-session variability and its efficient handling of high-dimensional multivariate time series data highlight its potential for advancing HD-sEMG-powered HCI systems.