![[2502.17457] MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2502.17457] MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition
Summary
The paper presents MoEMba, a novel framework utilizing Mamba-based Mixture of Experts for enhancing high-density EMG-based hand gesture recognition, addressing inter-session variability challenges.
Why It Matters
This research is significant as it tackles the critical issue of accuracy in HD-sEMG systems, which is essential for improving human-computer interaction. By introducing a robust framework that enhances gesture recognition, it opens avenues for more reliable applications in assistive technologies and user interfaces.
Key Takeaways
- MoEMba improves accuracy in HD-sEMG gesture recognition.
- The framework effectively addresses session-to-session variability.
- Wavelet feature modulation enhances signal representation.
- Experimental results show MoEMba outperforms existing methods.
- The approach is applicable for advancing HCI systems.
Electrical Engineering and Systems Science > Signal Processing arXiv:2502.17457 (eess) [Submitted on 9 Feb 2025 (v1), last revised 24 Feb 2026 (this version, v2)] Title:MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition Authors:Mehran Shabanpour, Kasra Rad, Sadaf Khademi, Arash Mohammadi View a PDF of the paper titled MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition, by Mehran Shabanpour and 3 other authors View PDF HTML (experimental) 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 ...
