A Lightweight Network with Domain Adaptation for Motor Imagery Recognition
Brain–computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the motor control and assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times and limited cross-subjec...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/27/1/14 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588573436542976 |
|---|---|
| author | Xinmin Ding Zenghui Zhang Kun Wang Xiaolin Xiao Minpeng Xu |
| author_facet | Xinmin Ding Zenghui Zhang Kun Wang Xiaolin Xiao Minpeng Xu |
| author_sort | Xinmin Ding |
| collection | DOAJ |
| description | Brain–computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the motor control and assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times and limited cross-subject adaptability, which restrict their practical application. This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A lightweight feature extraction module is designed to extract key features from both the source and target domains, effectively reducing the model’s parameters and improving the real-time performance and computational efficiency. To address differences in sample distributions, a domain adaptation strategy is introduced to optimize the feature alignment. Furthermore, domain adversarial training is employed to promote the learning of domain-invariant features, significantly enhancing the model’s cross-subject generalization ability. The proposed method was evaluated on an fNIRS motor imagery dataset, achieving an average accuracy of 87.76% in a three-class classification task. Additionally, lightweight experiments were conducted from two perspectives: model structure optimization and data feature selection. The results demonstrated the potential advantages of this method for practical applications in motor imagery recognition systems. |
| format | Article |
| id | doaj-art-b1c1d6e4269344aba2669915b869cb6f |
| institution | Kabale University |
| issn | 1099-4300 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-b1c1d6e4269344aba2669915b869cb6f2025-01-24T13:31:39ZengMDPI AGEntropy1099-43002024-12-012711410.3390/e27010014A Lightweight Network with Domain Adaptation for Motor Imagery RecognitionXinmin Ding0Zenghui Zhang1Kun Wang2Xiaolin Xiao3Minpeng Xu4Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300384, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300384, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300384, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300384, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300384, ChinaBrain–computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the motor control and assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times and limited cross-subject adaptability, which restrict their practical application. This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A lightweight feature extraction module is designed to extract key features from both the source and target domains, effectively reducing the model’s parameters and improving the real-time performance and computational efficiency. To address differences in sample distributions, a domain adaptation strategy is introduced to optimize the feature alignment. Furthermore, domain adversarial training is employed to promote the learning of domain-invariant features, significantly enhancing the model’s cross-subject generalization ability. The proposed method was evaluated on an fNIRS motor imagery dataset, achieving an average accuracy of 87.76% in a three-class classification task. Additionally, lightweight experiments were conducted from two perspectives: model structure optimization and data feature selection. The results demonstrated the potential advantages of this method for practical applications in motor imagery recognition systems.https://www.mdpi.com/1099-4300/27/1/14BCImotor imagerytransfer learningconvolutional neural network |
| spellingShingle | Xinmin Ding Zenghui Zhang Kun Wang Xiaolin Xiao Minpeng Xu A Lightweight Network with Domain Adaptation for Motor Imagery Recognition Entropy BCI motor imagery transfer learning convolutional neural network |
| title | A Lightweight Network with Domain Adaptation for Motor Imagery Recognition |
| title_full | A Lightweight Network with Domain Adaptation for Motor Imagery Recognition |
| title_fullStr | A Lightweight Network with Domain Adaptation for Motor Imagery Recognition |
| title_full_unstemmed | A Lightweight Network with Domain Adaptation for Motor Imagery Recognition |
| title_short | A Lightweight Network with Domain Adaptation for Motor Imagery Recognition |
| title_sort | lightweight network with domain adaptation for motor imagery recognition |
| topic | BCI motor imagery transfer learning convolutional neural network |
| url | https://www.mdpi.com/1099-4300/27/1/14 |
| work_keys_str_mv | AT xinminding alightweightnetworkwithdomainadaptationformotorimageryrecognition AT zenghuizhang alightweightnetworkwithdomainadaptationformotorimageryrecognition AT kunwang alightweightnetworkwithdomainadaptationformotorimageryrecognition AT xiaolinxiao alightweightnetworkwithdomainadaptationformotorimageryrecognition AT minpengxu alightweightnetworkwithdomainadaptationformotorimageryrecognition AT xinminding lightweightnetworkwithdomainadaptationformotorimageryrecognition AT zenghuizhang lightweightnetworkwithdomainadaptationformotorimageryrecognition AT kunwang lightweightnetworkwithdomainadaptationformotorimageryrecognition AT xiaolinxiao lightweightnetworkwithdomainadaptationformotorimageryrecognition AT minpengxu lightweightnetworkwithdomainadaptationformotorimageryrecognition |