Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture
Abstract Surface electromyography (sEMG) data has been extensively utilized in deep learning algorithms for hand movement classification. This paper aims to introduce a novel method for hand gesture classification using sEMG data, addressing accuracy challenges seen in previous studies. We propose a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82676-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850103040534642688 |
|---|---|
| author | Khosro Rezaee Safoura Farsi Khavari Mojtaba Ansari Fatemeh Zare Mohammad Hossein Alizadeh Roknabadi |
| author_facet | Khosro Rezaee Safoura Farsi Khavari Mojtaba Ansari Fatemeh Zare Mohammad Hossein Alizadeh Roknabadi |
| author_sort | Khosro Rezaee |
| collection | DOAJ |
| description | Abstract Surface electromyography (sEMG) data has been extensively utilized in deep learning algorithms for hand movement classification. This paper aims to introduce a novel method for hand gesture classification using sEMG data, addressing accuracy challenges seen in previous studies. We propose a U-Net architecture incorporating a MobileNetV2 encoder, enhanced by a novel Bidirectional Long Short-Term Memory (BiLSTM) and metaheuristic optimization for spatial feature extraction in hand gesture and motion recognition. Bayesian optimization is employed as the metaheuristic approach to optimize the BiLSTM model’s architecture. To address the non-stationarity of sEMG signals, we employ a windowing strategy for signal augmentation within deep learning architectures. The MobileNetV2 encoder and U-Net architecture extract relevant features from sEMG spectrogram images. Edge computing integration is leveraged to further enhance innovation by enabling real-time processing and decision-making closer to the data source. Six standard databases were utilized, achieving an average accuracy of 90.23% with our proposed model, showcasing a 3–4% average accuracy improvement and a 10% variance reduction. Notably, Mendeley Data, BioPatRec DB3, and BioPatRec DB1 surpassed advanced models in their respective domains with classification accuracies of 88.71%, 90.2%, and 88.6%, respectively. Experimental results underscore the significant enhancement in generalizability and gesture recognition robustness. This approach offers a fresh perspective on prosthetic management and human-machine interaction, emphasizing its efficacy in improving accuracy and reducing variance for enhanced prosthetic control and interaction with machines through edge computing integration. |
| format | Article |
| id | doaj-art-923b9cc260144d03ba25d6e027773eb2 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-923b9cc260144d03ba25d6e027773eb22025-08-20T02:39:38ZengNature PortfolioScientific Reports2045-23222024-12-0114112010.1038/s41598-024-82676-1Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architectureKhosro Rezaee0Safoura Farsi Khavari1Mojtaba Ansari2Fatemeh Zare3Mohammad Hossein Alizadeh Roknabadi4Department of Biomedical Engineering, Meybod UniversityDepartment of Electrical Engineering, Ferdowsi University of MashhadDepartment of Biomedical Engineering, Meybod UniversityDepartment of Electrical and Computer Engineering, Texas A&M UniversityDepartment of Electrical Engineering, Amirkabir University of TechnologyAbstract Surface electromyography (sEMG) data has been extensively utilized in deep learning algorithms for hand movement classification. This paper aims to introduce a novel method for hand gesture classification using sEMG data, addressing accuracy challenges seen in previous studies. We propose a U-Net architecture incorporating a MobileNetV2 encoder, enhanced by a novel Bidirectional Long Short-Term Memory (BiLSTM) and metaheuristic optimization for spatial feature extraction in hand gesture and motion recognition. Bayesian optimization is employed as the metaheuristic approach to optimize the BiLSTM model’s architecture. To address the non-stationarity of sEMG signals, we employ a windowing strategy for signal augmentation within deep learning architectures. The MobileNetV2 encoder and U-Net architecture extract relevant features from sEMG spectrogram images. Edge computing integration is leveraged to further enhance innovation by enabling real-time processing and decision-making closer to the data source. Six standard databases were utilized, achieving an average accuracy of 90.23% with our proposed model, showcasing a 3–4% average accuracy improvement and a 10% variance reduction. Notably, Mendeley Data, BioPatRec DB3, and BioPatRec DB1 surpassed advanced models in their respective domains with classification accuracies of 88.71%, 90.2%, and 88.6%, respectively. Experimental results underscore the significant enhancement in generalizability and gesture recognition robustness. This approach offers a fresh perspective on prosthetic management and human-machine interaction, emphasizing its efficacy in improving accuracy and reducing variance for enhanced prosthetic control and interaction with machines through edge computing integration.https://doi.org/10.1038/s41598-024-82676-1Hand GestureEdge computingsEMGBiLSTMBayesian optimizationMobileNetV2 |
| spellingShingle | Khosro Rezaee Safoura Farsi Khavari Mojtaba Ansari Fatemeh Zare Mohammad Hossein Alizadeh Roknabadi Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture Scientific Reports Hand Gesture Edge computing sEMG BiLSTM Bayesian optimization MobileNetV2 |
| title | Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture |
| title_full | Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture |
| title_fullStr | Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture |
| title_full_unstemmed | Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture |
| title_short | Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture |
| title_sort | hand gestures classification of semg signals based on bilstm metaheuristic optimization and hybrid u net mobilenetv2 encoder architecture |
| topic | Hand Gesture Edge computing sEMG BiLSTM Bayesian optimization MobileNetV2 |
| url | https://doi.org/10.1038/s41598-024-82676-1 |
| work_keys_str_mv | AT khosrorezaee handgesturesclassificationofsemgsignalsbasedonbilstmmetaheuristicoptimizationandhybridunetmobilenetv2encoderarchitecture AT safourafarsikhavari handgesturesclassificationofsemgsignalsbasedonbilstmmetaheuristicoptimizationandhybridunetmobilenetv2encoderarchitecture AT mojtabaansari handgesturesclassificationofsemgsignalsbasedonbilstmmetaheuristicoptimizationandhybridunetmobilenetv2encoderarchitecture AT fatemehzare handgesturesclassificationofsemgsignalsbasedonbilstmmetaheuristicoptimizationandhybridunetmobilenetv2encoderarchitecture AT mohammadhosseinalizadehroknabadi handgesturesclassificationofsemgsignalsbasedonbilstmmetaheuristicoptimizationandhybridunetmobilenetv2encoderarchitecture |