TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Kuan-Chen, Liu, Kai-Chun, Yeh, Ping-Cheng, Peng, Sheng-Yu, Tsao, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929533081354240
author Wang, Kuan-Chen
Liu, Kai-Chun
Yeh, Ping-Cheng
Peng, Sheng-Yu
Tsao, Yu
author_facet Wang, Kuan-Chen
Liu, Kai-Chun
Yeh, Ping-Cheng
Peng, Sheng-Yu
Tsao, Yu
contents Surface electromyography (sEMG) is a widely employed bio-signal that captures human muscle activity via electrodes placed on the skin. Several studies have proposed methods to remove sEMG contaminants, as non-invasive measurements render sEMG susceptible to various contaminants. However, these approaches often rely on heuristic-based optimization and are sensitive to the contaminant type. A more potent, robust, and generalized sEMG denoising approach should be developed for various healthcare and human-computer interaction applications. This paper proposes a novel neural network (NN)-based sEMG denoising method called TrustEMG-Net. It leverages the potent nonlinear mapping capability and data-driven nature of NNs. TrustEMG-Net adopts a denoising autoencoder structure by combining U-Net with a Transformer encoder using a representation-masking approach. The proposed approach is evaluated using the Ninapro sEMG database with five common contamination types and signal-to-noise ratio (SNR) conditions. Compared with existing sEMG denoising methods, TrustEMG-Net achieves exceptional performance across the five evaluation metrics, exhibiting a minimum improvement of 20%. Its superiority is consistent under various conditions, including SNRs ranging from -14 to 2 dB and five contaminant types. An ablation study further proves that the design of TrustEMG-Net contributes to its optimality, providing high-quality sEMG and serving as an effective, robust, and generalized denoising solution for sEMG applications.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03843
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement
Wang, Kuan-Chen
Liu, Kai-Chun
Yeh, Ping-Cheng
Peng, Sheng-Yu
Tsao, Yu
Signal Processing
Machine Learning
Surface electromyography (sEMG) is a widely employed bio-signal that captures human muscle activity via electrodes placed on the skin. Several studies have proposed methods to remove sEMG contaminants, as non-invasive measurements render sEMG susceptible to various contaminants. However, these approaches often rely on heuristic-based optimization and are sensitive to the contaminant type. A more potent, robust, and generalized sEMG denoising approach should be developed for various healthcare and human-computer interaction applications. This paper proposes a novel neural network (NN)-based sEMG denoising method called TrustEMG-Net. It leverages the potent nonlinear mapping capability and data-driven nature of NNs. TrustEMG-Net adopts a denoising autoencoder structure by combining U-Net with a Transformer encoder using a representation-masking approach. The proposed approach is evaluated using the Ninapro sEMG database with five common contamination types and signal-to-noise ratio (SNR) conditions. Compared with existing sEMG denoising methods, TrustEMG-Net achieves exceptional performance across the five evaluation metrics, exhibiting a minimum improvement of 20%. Its superiority is consistent under various conditions, including SNRs ranging from -14 to 2 dB and five contaminant types. An ablation study further proves that the design of TrustEMG-Net contributes to its optimality, providing high-quality sEMG and serving as an effective, robust, and generalized denoising solution for sEMG applications.
title TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2410.03843