Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface
In the field of the muscle–computer interface, the most challenging task is extracting patterns from complex surface electromyography (sEMG) signals to improve the performance of myoelectric pattern recognition. To address this problem, a two-stage architecture, consisting of Gramian angular field (...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2715 |
| _version_ | 1797614329096306688 |
|---|---|
| author | Junjun Fan Jiajun Wen Zhihui Lai |
| author_facet | Junjun Fan Jiajun Wen Zhihui Lai |
| author_sort | Junjun Fan |
| collection | DOAJ |
| description | In the field of the muscle–computer interface, the most challenging task is extracting patterns from complex surface electromyography (sEMG) signals to improve the performance of myoelectric pattern recognition. To address this problem, a two-stage architecture, consisting of Gramian angular field (GAF)-based 2D representation and convolutional neural network (CNN)-based classification (GAF-CNN), is proposed. To explore discriminant channel features from sEMG signals, sEMG-GAF transformation is proposed for time sequence signal representation and feature modeling, in which the instantaneous values of multichannel sEMG signals are encoded in image form. A deep CNN model is introduced to extract high-level semantic features lying in image-form-based time sequence signals concerning instantaneous values for image classification. An insight analysis explains the rationale behind the advantages of the proposed method. Extensive experiments are conducted on benchmark publicly available sEMG datasets, i.e., NinaPro and CagpMyo, whose experimental results validate that the proposed GAF-CNN method is comparable to the state-of-the-art methods, as reported by previous work incorporating CNN models. |
| first_indexed | 2024-03-11T07:10:51Z |
| format | Article |
| id | doaj.art-d18ff9f4326943a1bd7083161d58c7ea |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:51Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d18ff9f4326943a1bd7083161d58c7ea2023-11-17T08:38:41ZengMDPI AGSensors1424-82202023-03-01235271510.3390/s23052715Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer InterfaceJunjun Fan0Jiajun Wen1Zhihui Lai2College of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518060, ChinaIn the field of the muscle–computer interface, the most challenging task is extracting patterns from complex surface electromyography (sEMG) signals to improve the performance of myoelectric pattern recognition. To address this problem, a two-stage architecture, consisting of Gramian angular field (GAF)-based 2D representation and convolutional neural network (CNN)-based classification (GAF-CNN), is proposed. To explore discriminant channel features from sEMG signals, sEMG-GAF transformation is proposed for time sequence signal representation and feature modeling, in which the instantaneous values of multichannel sEMG signals are encoded in image form. A deep CNN model is introduced to extract high-level semantic features lying in image-form-based time sequence signals concerning instantaneous values for image classification. An insight analysis explains the rationale behind the advantages of the proposed method. Extensive experiments are conducted on benchmark publicly available sEMG datasets, i.e., NinaPro and CagpMyo, whose experimental results validate that the proposed GAF-CNN method is comparable to the state-of-the-art methods, as reported by previous work incorporating CNN models.https://www.mdpi.com/1424-8220/23/5/2715muscle–computer interfacesurface electromyographymyoelectric pattern recognitionGramian angular fieldconvolutional neural networks |
| spellingShingle | Junjun Fan Jiajun Wen Zhihui Lai Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface Sensors muscle–computer interface surface electromyography myoelectric pattern recognition Gramian angular field convolutional neural networks |
| title | Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface |
| title_full | Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface |
| title_fullStr | Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface |
| title_full_unstemmed | Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface |
| title_short | Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface |
| title_sort | myoelectric pattern recognition using gramian angular field and convolutional neural networks for muscle computer interface |
| topic | muscle–computer interface surface electromyography myoelectric pattern recognition Gramian angular field convolutional neural networks |
| url | https://www.mdpi.com/1424-8220/23/5/2715 |
| work_keys_str_mv | AT junjunfan myoelectricpatternrecognitionusinggramianangularfieldandconvolutionalneuralnetworksformusclecomputerinterface AT jiajunwen myoelectricpatternrecognitionusinggramianangularfieldandconvolutionalneuralnetworksformusclecomputerinterface AT zhihuilai myoelectricpatternrecognitionusinggramianangularfieldandconvolutionalneuralnetworksformusclecomputerinterface |