# Research on the recognition model of exercise fatigue based on the fusion of sEMG and ECG signals

## TL;DR

This paper improves wearable device accuracy in detecting exercise fatigue by combining sEMG and ECG signals with advanced noise reduction techniques.

## Contribution

A novel denoising method using ISSA-VMD-SWT is proposed to enhance fatigue state recognition accuracy.

## Key findings

- The method achieved 93.25% accuracy for 'Easy' exercise state identification.
- It reached 95.16% accuracy for the 'Transition' state and 93.05% for the 'Tired' state.
- The approach outperforms traditional denoising techniques in preserving fatigue-related features.

## Abstract

This study significantly enhances the accuracy of exercise state identification in wearable devices through improved denoising techniques for sEMG and ECG signals. By adopting an optimized Variational Mode Decomposition (VMD) method, combined with the Improved Sparrow Search Algorithm and Second Generation Wavelet Transform (ISSA-VMD-SWT), and introducing chaos mapping to strengthen the algorithm’s initial population, this approach effectively reduces noise while preserving key fatigue-related features. In tests conducted on data from 32 participants, the method achieved accuracy rates of 93.25%, 95.16%, and 93.05% for identifying “Easy,” “Transition,” and “Tired” exercise states, respectively, showing significant advantages over traditional denoising techniques. These results indicate that the denoising technology developed in this study represents a significant technological advancement for the application of ECG and sEMG fatigue identification technologies in wearable health monitoring devices.

•Proposes an enhanced sparrow search algorithm with second-gen wavelet transform•Overcomes slow convergence and local solution issues, enhancing denoising effect•Proposed method enhances denoising, leading to higher accuracy in fatigue recognition model

Proposes an enhanced sparrow search algorithm with second-gen wavelet transform

Overcomes slow convergence and local solution issues, enhancing denoising effect

Proposed method enhances denoising, leading to higher accuracy in fatigue recognition model

Health sciences; Medicine; Medical specialty; Internal medicine; Cardiovascular medicine; Natural sciences; Biological sciences; Biology experimental methods