Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition

2026-01-07

arXiv.org

AI Summary

This study addresses the degradation in cross-session surface electromyography (sEMG) recognition performance caused by electrode displacement, muscle fatigue, and posture variations. To mitigate this issue, the authors propose a lightweight test-time adaptation framework built upon a temporal convolutional network (TCN), incorporating three deployment-friendly strategies: causal adaptive batch normalization, Gaussian mixture model–based distribution alignment enhanced with experience replay, and a meta-learning mechanism tailored for rapid few-shot calibration. Experimental results on the NinaPro DB6 dataset demonstrate that the proposed approach substantially narrows the cross-session accuracy gap. Notably, the experience replay strategy exhibits the most robust performance under data-scarce conditions, while the meta-learning component achieves state-of-the-art results in both one- and two-shot calibration scenarios.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Reliable long-term decoding of surface electromyography (EMG) is hindered by signal drift caused by electrode shifts, muscle fatigue, and posture changes. While state-of-the-art models achieve high intra-session accuracy, their performance often degrades sharply. Existing solutions typically demand large datasets or high-compute pipelines that are impractical for energy-efficient wearables. We propose a lightweight framework for Test-Time Adaptation (TTA) using a Temporal Convolutional Network (TCN) backbone. We introduce three deployment-ready strategies: (i) causal adaptive batch normalization for real-time statistical alignment; (ii) a Gaussian Mixture Model (GMM) alignment with experience replay to prevent forgetting; and (iii) meta-learning for rapid, few-shot calibration. Evaluated on the NinaPro DB6 multi-session dataset, our framework significantly bridges the inter-session accuracy gap with minimal overhead. Our results show that experience-replay updates yield superior stability under limited data, while meta-learning achieves competitive performance in one- and two-shot regimes using only a fraction of the data required by current benchmarks. This work establishes a path toward robust,"plug-and-play"myoelectric control for long-term prosthetic use.

Problem

• EMG-based gesture recognition
• signal drift
• test-time adaptation
• long-term decoding
• wearable devices

Innovation

• Test-Time Adaptation
• Temporal Convolutional Network
• Experience Replay
• Meta-Learning
• EMG Gesture Recognition