Deep Residual U-Net Autoencoder with Weighted Overlapping Reconstruction for EMG Signal Denoising

Electromyography (EMG) signals, crucial for neuromuscular assessment, are frequently corrupted by noise, impairing signal fidelity and subsequent analysis across diverse applications. Conventional filters often inadequately address non-stationary noise or introduce signal distortion. This paper intr...

Full description

Saved in:
Bibliographic Details
Published in:Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference proceedings pp. 198 - 203
Main Authors: Mehmood, Atif, Wiora, Jozef
Format: Conference Proceeding
Language:English
Published: Division of Signal Processing and Electronic Syste 17.09.2025
Subjects:
Autoencoders
Convolution
Convolutional Autoencoder (CAE)
Deep learning
Electromyography
Electromyography (EMG)
Noise measurement
Noise reduction
Residual Networks
Signal denoising
Signal Processing
Signal to noise ratio
Synthetic data
Synthetic Data Generation
Training
U-Net
ISBN:9788362065493, 8362065494
ISSN:2326-0262
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Electromyography (EMG) signals, crucial for neuromuscular assessment, are frequently corrupted by noise, impairing signal fidelity and subsequent analysis across diverse applications. Conventional filters often inadequately address non-stationary noise or introduce signal distortion. This paper introduces an advanced deep learning framework for EMG denoising, centred on a U-Net-inspired convolutional autoencoder with integrated residual blocks and skip connections. Training utilised synthetic EMG data, closely emulating physiological frequency bands and burst dynamics, subsequently corrupted by a comprehensive noise model encompassing electrode, crosstalk, electronic, drift, and contact artefacts. Training was guided by a custom loss function that combined weighted mean squared error (MSE) with signal-to-noise ratio (SNR). The proposed autoencoder achieved substantial improvements, SNR increased from -0.95 dB (noisy) to 14.64 dB (denoised), and MSE was drastically reduced from 0.001493 V 2 to 0.000041 V 2 on the test dataset. Qualitative analysis confirmed effective noise suppression while retaining crucial EMG burst characteristics. This advanced framework offers a promising solution for robust restoration of EMG signals in practical settings.
AbstractList Electromyography (EMG) signals, crucial for neuromuscular assessment, are frequently corrupted by noise, impairing signal fidelity and subsequent analysis across diverse applications. Conventional filters often inadequately address non-stationary noise or introduce signal distortion. This paper introduces an advanced deep learning framework for EMG denoising, centred on a U-Net-inspired convolutional autoencoder with integrated residual blocks and skip connections. Training utilised synthetic EMG data, closely emulating physiological frequency bands and burst dynamics, subsequently corrupted by a comprehensive noise model encompassing electrode, crosstalk, electronic, drift, and contact artefacts. Training was guided by a custom loss function that combined weighted mean squared error (MSE) with signal-to-noise ratio (SNR). The proposed autoencoder achieved substantial improvements, SNR increased from -0.95 dB (noisy) to 14.64 dB (denoised), and MSE was drastically reduced from 0.001493 V 2 to 0.000041 V 2 on the test dataset. Qualitative analysis confirmed effective noise suppression while retaining crucial EMG burst characteristics. This advanced framework offers a promising solution for robust restoration of EMG signals in practical settings.
Author Mehmood, Atif
Wiora, Jozef
Author_xml – sequence: 1
  givenname: Atif
  surname: Mehmood
  fullname: Mehmood, Atif
  email: atif.mehmood@polsl.pl
  organization: Silesian University of Technology,Department of Measurements and Control Systems,Gliwice,Poland,44-100
– sequence: 2
  givenname: Jozef
  surname: Wiora
  fullname: Wiora, Jozef
  email: jozef.wiora@polsl.pl
  organization: Silesian University of Technology,Department of Measurements and Control Systems,Gliwice,Poland,44-100
BookMark eNo1kN1KwzAcxSNOcJt9A8G8QGe-mjaXY18K04mbeDnS5N8uMpPSZopvb8F5dTicc34XZ4QGPnhA6I6SCeOKqvvty1RmGc8njLBsQimjGaXiAo0KLhnpIyovUaLy4uyF4gM0ZJzJlDDJrlHSdR-EECqLHiiHSM8BGvwKnbMnfcRv6TNEPD3FAN4ECy3-dvGA38HVhwgWb76gPeqmcb7uRyb4LrYnE13wuAotXjyt8NbVvifNwQfX9b0bdFXpYwfJWcdot1zsZg_perN6nE3XqVM8piVRglsDjJUVNXkpM6W1qKSxSoiCC0usKpW1IJXOCSemAMmysrC5ZVabio_R7R_WAcC-ad2nbn_2_w_xX8IwW8o
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.23919/SPA65537.2025.11215114
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 8362065516
9788362065516
EndPage 203
ExternalDocumentID 11215114
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
ID FETCH-LOGICAL-i93t-b0943dce22bf1c7b659aa4f6cd944834d0d9b9dde69a7030c8e625b8d7d2dacf3
IEDL.DBID RIE
ISBN 9788362065493
8362065494
ISSN 2326-0262
IngestDate Wed Nov 05 07:12:47 EST 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-b0943dce22bf1c7b659aa4f6cd944834d0d9b9dde69a7030c8e625b8d7d2dacf3
PageCount 6
ParticipantIDs ieee_primary_11215114
PublicationCentury 2000
PublicationDate 2025-Sept.-17
PublicationDateYYYYMMDD 2025-09-17
PublicationDate_xml – month: 09
  year: 2025
  text: 2025-Sept.-17
  day: 17
PublicationDecade 2020
PublicationTitle Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference proceedings
PublicationTitleAbbrev SPA
PublicationYear 2025
Publisher Division of Signal Processing and Electronic Syste
Publisher_xml – name: Division of Signal Processing and Electronic Syste
SSID ssj0001682396
Score 1.921786
Snippet Electromyography (EMG) signals, crucial for neuromuscular assessment, are frequently corrupted by noise, impairing signal fidelity and subsequent analysis...
SourceID ieee
SourceType Publisher
StartPage 198
SubjectTerms Autoencoders
Convolution
Convolutional Autoencoder (CAE)
Deep learning
Electromyography
Electromyography (EMG)
Noise measurement
Noise reduction
Residual Networks
Signal denoising
Signal Processing
Signal to noise ratio
Synthetic data
Synthetic Data Generation
Training
U-Net
Title Deep Residual U-Net Autoencoder with Weighted Overlapping Reconstruction for EMG Signal Denoising
URI https://ieeexplore.ieee.org/document/11215114
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYoCFVxFveWBNm8SJH2NFW1goFS2iW-XYlypLUrVpfz--pA8YGNjiSFGSs3Xn-3zfd4Q8uZAeMA3MCyA1XsQD60nlay-0MlQaOM561WxCDAZyMlHDDVm94sIAQFV8Bi28rM7ybWFWCJW1A5RCCLBt9aEQvCZr7QEVLkOm6mZyIRbWcszCpHPQyJ_ciADK3ZjVxV7ukUC1R8MOj2MmXL4Yxq3ta341XKniTf_0n196Rpp75h4d7mLSOTmA_IKc_BAdvCS6CzCnH7CsaFj00xtASTurskBJSwsLitAs_aogU7D0fY2IH6o4zCjmqnvFWer2u7T39kJH2cwtR9qFvMgQemiScb83fn71No0WvEyx0kuwutAaCMMkDYxIeKy0jlJurIoQa7S-VYlyfpArjQ7CSHBZUyKtsKHVJmVXpJEXOVwTGjnXL2PLJBeRsznq24FvmPMLqW9lLG9IE401nddSGtOtnW7_uH9HjnFKsEAjEPek4f4QHsiRWZfZcvFYLYBvpA-qSw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8JAEN0YNFEvfmH8dg9eC2233e4eiYAYoRLByI20u1PCpSVQ-P3ulAJ68OCtbdK0nd3Mdt7Oe4-QJ7OkOywCZjmQKMvjjraEtCPL1cKVEXAc9cJsIghDMRrJfklWL7gwAFA0n0END4u9fJ2pJUJldQelEBy0rd5H66ySrrWDVLhwmVzbybnYWsuxDhMmRSODspQBFNtztm73Mrc4sj7oN7jvs8BUjK5f2zzol-VKseK0T_75rqekuuPu0f52VToje5Cek-MfsoMXJGoCzOgHLAoiFv20QshpY5lnKGqpYU4RnKVfBWgKmr6vEPNDHYcJxWp1pzlLzR8vbfVe6GA6MROSNiHNpgg-VMmw3Ro-d6zSasGaSpZbMfYXagWuGyeOCmLuyyjyEq609BBt1LaWsTSZkMsIU4QSYOqmWOhAuzpSCbsklTRL4YpQzyR_4WsmeOCZmKPCHdiKmcyQ2Fr44ppUMVjj2VpMY7yJ080f1x_JYWfY6467r-HbLTnC4cF2DSe4IxXztXBPDtQqny7mD8Vk-Aa3vq2U
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Signal+Processing+Algorithms%2C+Architectures%2C+Arrangements%2C+and+Applications+Conference+proceedings&rft.atitle=Deep+Residual+U-Net+Autoencoder+with+Weighted+Overlapping+Reconstruction+for+EMG+Signal+Denoising&rft.au=Mehmood%2C+Atif&rft.au=Wiora%2C+Jozef&rft.date=2025-09-17&rft.pub=Division+of+Signal+Processing+and+Electronic+Syste&rft.isbn=9788362065493&rft.issn=2326-0262&rft.spage=198&rft.epage=203&rft_id=info:doi/10.23919%2FSPA65537.2025.11215114&rft.externalDocID=11215114
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2326-0262&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2326-0262&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2326-0262&client=summon