Efficient and Robust Spiking Neural Networks for sEMG-Based Muscle Fatigue Detection

2026-07-13

AI Summary

This study addresses the challenge of real-time muscle fatigue detection using surface electromyography (sEMG), which is hindered by the high computational cost and data dependency of conventional deep learning methods. To overcome these limitations, the authors propose a low-power spiking neural network (SNN) framework that leverages event-driven sparse computation and temporal modeling capabilities. They further introduce a quantization-aware training strategy, termed SDH, which integrates multiple regularization terms to enhance model robustness and energy efficiency under noisy conditions. Evaluated on two public sEMG datasets across seven noise scenarios, the proposed quantized SNN matches or surpasses strong baselines in performance while demonstrating superior stability and achieving up to a 201.77-fold reduction in energy consumption.

Abstract

Detecting muscle fatigue via surface electromyography (sEMG) is essential for applications in sports, rehabilitation, and wearable health monitoring. Accurate and timely detection of fatigue is crucial for preventing injuries, optimizing physical performance, and ensuring user safety during prolonged activity. However, existing deep learning models are often unsuitable for this task due to their high computational cost and dependence on large-scale data. In this work, we propose an energy-efficient framework for muscle fatigue detection based on Spiking Neural Networks (SNNs), which exploit sparse, event-driven computation and temporal modeling. We further introduce a quantization-compatible training scheme (SDH) that combines multiple regularization terms to improve robustness under noisy conditions. Evaluated on two public sEMG datasets against a broad set of baselines and under seven noise conditions including physically motivated perturbations, our quantized SNNs match or exceed strong baselines while remaining more stable under diverse noise and reducing estimated energy consumption by up to 201.77x. These results demonstrate the framework's strong potential for real-time deployment in low-power wearable systems.

Problem

• muscle fatigue detection
• surface electromyography
• spiking neural networks
• energy efficiency
• robustness

Innovation

• Spiking Neural Networks
• sEMG
• muscle fatigue detection
• quantization
• energy efficiency