A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model

Physical fatigue significantly impacts safety and performance across industrial, athletic, and medical domains, yet its detection remains challenging due to individual variability and limited generalizability of existing methods. This study introduces a multimodal fatigue detection system integratin...

Full description

Saved in:
Bibliographic Details
Main Authors: Soree Hwang, Nayeon Kwon, Dongwon Lee, Jongman Kim, Sumin Yang, Inchan Youn, Hyuk-June Moon, Joon-Kyung Sung, Sungmin Han
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330979050618880
author Soree Hwang
Nayeon Kwon
Dongwon Lee
Jongman Kim
Sumin Yang
Inchan Youn
Hyuk-June Moon
Joon-Kyung Sung
Sungmin Han
author_facet Soree Hwang
Nayeon Kwon
Dongwon Lee
Jongman Kim
Sumin Yang
Inchan Youn
Hyuk-June Moon
Joon-Kyung Sung
Sungmin Han
author_sort Soree Hwang
collection DOAJ
description Physical fatigue significantly impacts safety and performance across industrial, athletic, and medical domains, yet its detection remains challenging due to individual variability and limited generalizability of existing methods. This study introduces a multimodal fatigue detection system integrating surface electromyography (sEMG) and inertial measurement unit (IMU) signals, processed through a hybrid convolutional neural network–long short-term memory–attention (CNN-LSTM-Attention) model. Fatigue was induced in 35 healthy participants via step-up-and-down exercises, with gait data collected during natural walking before and after fatigue. The model leverages sEMG from the gastrocnemius lateralis and IMU-derived jerk signals from the tibialis anterior and rectus femoris to classify fatigue states. Evaluated using leave-one-subject-out cross-validation (LOSOCV), the system achieved an accuracy of 87.94% with bilateral EMG signals and a balanced recall of 87.94% for fatigued states using a combined IMU-EMG approach. These results highlight the system’s robustness for personalized fatigue monitoring, surpassing traditional subject-dependent methods by addressing inter-individual differences.
format Article
id doaj-art-b047e1f9ea3d4e6387cd88e0285ffe5d
institution Kabale University
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b047e1f9ea3d4e6387cd88e0285ffe5d2025-08-20T03:46:46ZengMDPI AGSensors1424-82202025-05-012511330910.3390/s25113309A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention ModelSoree Hwang0Nayeon Kwon1Dongwon Lee2Jongman Kim3Sumin Yang4Inchan Youn5Hyuk-June Moon6Joon-Kyung Sung7Sungmin Han8Bionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaSchool of Biomedical Engineering, Korea University, Seoul 02841, Republic of KoreaBionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of KoreaPhysical fatigue significantly impacts safety and performance across industrial, athletic, and medical domains, yet its detection remains challenging due to individual variability and limited generalizability of existing methods. This study introduces a multimodal fatigue detection system integrating surface electromyography (sEMG) and inertial measurement unit (IMU) signals, processed through a hybrid convolutional neural network–long short-term memory–attention (CNN-LSTM-Attention) model. Fatigue was induced in 35 healthy participants via step-up-and-down exercises, with gait data collected during natural walking before and after fatigue. The model leverages sEMG from the gastrocnemius lateralis and IMU-derived jerk signals from the tibialis anterior and rectus femoris to classify fatigue states. Evaluated using leave-one-subject-out cross-validation (LOSOCV), the system achieved an accuracy of 87.94% with bilateral EMG signals and a balanced recall of 87.94% for fatigued states using a combined IMU-EMG approach. These results highlight the system’s robustness for personalized fatigue monitoring, surpassing traditional subject-dependent methods by addressing inter-individual differences.https://www.mdpi.com/1424-8220/25/11/3309physical fatigue detectionsurface electromyography (sEMG)inertial measurement unit (IMU)hybrid deep learningCNN-LSTM-attentiongait kinematics
spellingShingle Soree Hwang
Nayeon Kwon
Dongwon Lee
Jongman Kim
Sumin Yang
Inchan Youn
Hyuk-June Moon
Joon-Kyung Sung
Sungmin Han
A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model
Sensors
physical fatigue detection
surface electromyography (sEMG)
inertial measurement unit (IMU)
hybrid deep learning
CNN-LSTM-attention
gait kinematics
title A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model
title_full A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model
title_fullStr A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model
title_full_unstemmed A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model
title_short A Multimodal Fatigue Detection System Using sEMG and IMU Signals with a Hybrid CNN-LSTM-Attention Model
title_sort multimodal fatigue detection system using semg and imu signals with a hybrid cnn lstm attention model
topic physical fatigue detection
surface electromyography (sEMG)
inertial measurement unit (IMU)
hybrid deep learning
CNN-LSTM-attention
gait kinematics
url https://www.mdpi.com/1424-8220/25/11/3309
work_keys_str_mv AT soreehwang amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT nayeonkwon amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT dongwonlee amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT jongmankim amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT suminyang amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT inchanyoun amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT hyukjunemoon amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT joonkyungsung amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT sungminhan amultimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT soreehwang multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT nayeonkwon multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT dongwonlee multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT jongmankim multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT suminyang multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT inchanyoun multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT hyukjunemoon multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT joonkyungsung multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel
AT sungminhan multimodalfatiguedetectionsystemusingsemgandimusignalswithahybridcnnlstmattentionmodel