sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder
This work presents a semi-supervised multilayer neural network (MLNN) with an Autoencoder to develop a classification model for recognizing hand gestures from electromyographic (EMG) signals. Using a Myo armband equipped with eight non-invasive surface-mounted biosensors, raw surface EMG (sEMG) sens...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Systems and Soft Computing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772941924000735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846115509915877376 |
|---|---|
| author | Hussein Naser Hashim A. Hashim |
| author_facet | Hussein Naser Hashim A. Hashim |
| author_sort | Hussein Naser |
| collection | DOAJ |
| description | This work presents a semi-supervised multilayer neural network (MLNN) with an Autoencoder to develop a classification model for recognizing hand gestures from electromyographic (EMG) signals. Using a Myo armband equipped with eight non-invasive surface-mounted biosensors, raw surface EMG (sEMG) sensor data were captured corresponding to five hand gestures: Fist, Open hand, Wave in, Wave out, and Double tap. The sensor collected data underwent preprocessing, feature extraction, label assignment, and dataset organization for classification tasks. The model implementation, validation, and testing demonstrated its efficacy after incorporating synthetic sEMG data generated by an Autoencoder. In comparison to the state-of-the-art techniques from the literature, the proposed model exhibited strong performance, achieving accuracy of 99.68%, 100%, and 99.26% during training, validation, and testing, respectively. Comparatively, the proposed MLNN with Autoencoder model outperformed a K-Nearest Neighbors model established for comparative evaluation. |
| format | Article |
| id | doaj-art-2565e2355bcc4e1ab4f900ea537ea3a3 |
| institution | Kabale University |
| issn | 2772-9419 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Systems and Soft Computing |
| spelling | doaj-art-2565e2355bcc4e1ab4f900ea537ea3a32024-12-19T11:03:11ZengElsevierSystems and Soft Computing2772-94192024-12-016200144sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with AutoencoderHussein Naser0Hashim A. Hashim1Department of Mechanical and Aerospace Engineering, Carleton University, Ottawa, ON, K1S-5B6, Canada; Department of Biomedical Engineering, University of Thi-Qar, Thi Qar, Nasiriyah, 64001, IraqDepartment of Mechanical and Aerospace Engineering, Carleton University, Ottawa, ON, K1S-5B6, Canada; Corresponding author.This work presents a semi-supervised multilayer neural network (MLNN) with an Autoencoder to develop a classification model for recognizing hand gestures from electromyographic (EMG) signals. Using a Myo armband equipped with eight non-invasive surface-mounted biosensors, raw surface EMG (sEMG) sensor data were captured corresponding to five hand gestures: Fist, Open hand, Wave in, Wave out, and Double tap. The sensor collected data underwent preprocessing, feature extraction, label assignment, and dataset organization for classification tasks. The model implementation, validation, and testing demonstrated its efficacy after incorporating synthetic sEMG data generated by an Autoencoder. In comparison to the state-of-the-art techniques from the literature, the proposed model exhibited strong performance, achieving accuracy of 99.68%, 100%, and 99.26% during training, validation, and testing, respectively. Comparatively, the proposed MLNN with Autoencoder model outperformed a K-Nearest Neighbors model established for comparative evaluation.http://www.sciencedirect.com/science/article/pii/S2772941924000735Electromyographic signalsNeural NetworksClassificationMyo armbandAutoencoder |
| spellingShingle | Hussein Naser Hashim A. Hashim sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder Systems and Soft Computing Electromyographic signals Neural Networks Classification Myo armband Autoencoder |
| title | sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder |
| title_full | sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder |
| title_fullStr | sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder |
| title_full_unstemmed | sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder |
| title_short | sEMG-based hand gestures classification using a semi-supervised multi-layer neural networks with Autoencoder |
| title_sort | semg based hand gestures classification using a semi supervised multi layer neural networks with autoencoder |
| topic | Electromyographic signals Neural Networks Classification Myo armband Autoencoder |
| url | http://www.sciencedirect.com/science/article/pii/S2772941924000735 |
| work_keys_str_mv | AT husseinnaser semgbasedhandgesturesclassificationusingasemisupervisedmultilayerneuralnetworkswithautoencoder AT hashimahashim semgbasedhandgesturesclassificationusingasemisupervisedmultilayerneuralnetworkswithautoencoder |