Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces
Deep learning technology is rapidly spreading in recent years and has been extensive attempts in the field of Brain-Computer Interface (BCI). Though the accuracy of Motor Imagery (MI) BCI systems based on the deep learning have been greatly improved compared with some traditional algorithms, it is s...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9343873/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533420257148928 |
|---|---|
| author | Xin Deng Boxian Zhang Nian Yu Ke Liu Kaiwei Sun |
| author_facet | Xin Deng Boxian Zhang Nian Yu Ke Liu Kaiwei Sun |
| author_sort | Xin Deng |
| collection | DOAJ |
| description | Deep learning technology is rapidly spreading in recent years and has been extensive attempts in the field of Brain-Computer Interface (BCI). Though the accuracy of Motor Imagery (MI) BCI systems based on the deep learning have been greatly improved compared with some traditional algorithms, it is still a big problem to clearly interpret the deep learning models. To address the issues, this work first introduces a popular deep learning model EEGNet and compares it with the traditional algorithm Filter-Bank Common Spatial Pattern (FBCSP). After that, this work considers that the 1-D convolution of EEGNet can be explained by a special Discrete Wavelet Transform (DWT), and the depthwise convolution of EEGNet is similar to the Common Spatial Pattern (CSP) algorithm. Therefore, this work improves the EEGNet by using the algorithm Temporary Constrained Sparse Group Lasso (TCSGL) to enhance its performance. The proposed model TSGL-EEGNet is tested on the BCI Competition IV 2a and BCI Competition III IIIa datasets that both are 4-classes classification MI tasks. The testing results show that the proposed model has achieved 78.96% (0.7194) average classification accuracy (kappa) on the dataset BCI Competition IV 2a, which are greater than EEGNet, C2CM, MB3DCNN, SS-MEMDBF and FBCSP, especially on insensitive subjects. The proposed model has also achieved 85.30% (0.8040) average classification accuracy (kappa) on the dataset BCI Competition III IIIa, which are greater than the EEGNet, MFTFS <italic>et al.</italic> At last, this work uses average-validation and stacking to further enhance the effect of the model. The 4-classes classification average accuracy rates reach 81.34% and 88.89%, and the kappas reach 0.7511 and 0.8519 on dataset BCI Competition IV 2a and BCI Competition III IIIa, respectively. Additionally, this work also uses the Grad-CAM to visualize the frequency and spatial features that are learned by the neural network. |
| format | Article |
| id | doaj-art-87bf575301b243b2b22ad9dcd6cce28d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-87bf575301b243b2b22ad9dcd6cce28d2025-01-16T00:01:07ZengIEEEIEEE Access2169-35362021-01-019251182513010.1109/ACCESS.2021.30560889343873Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer InterfacesXin Deng0https://orcid.org/0000-0003-1257-694XBoxian Zhang1https://orcid.org/0000-0003-3805-519XNian Yu2https://orcid.org/0000-0002-8497-2426Ke Liu3https://orcid.org/0000-0001-8151-4326Kaiwei Sun4Key Laboratory of Data Engineering and Visual Computing, College of Computer Science and Technology, Chongqing University of Posts and Telecommunication, Chongqing, ChinaKey Laboratory of Data Engineering and Visual Computing, College of Computer Science and Technology, Chongqing University of Posts and Telecommunication, Chongqing, ChinaSchool of Electrical Engineering, Chongqing University, Chongqing, ChinaKey Laboratory of Data Engineering and Visual Computing, College of Computer Science and Technology, Chongqing University of Posts and Telecommunication, Chongqing, ChinaKey Laboratory of Data Engineering and Visual Computing, College of Computer Science and Technology, Chongqing University of Posts and Telecommunication, Chongqing, ChinaDeep learning technology is rapidly spreading in recent years and has been extensive attempts in the field of Brain-Computer Interface (BCI). Though the accuracy of Motor Imagery (MI) BCI systems based on the deep learning have been greatly improved compared with some traditional algorithms, it is still a big problem to clearly interpret the deep learning models. To address the issues, this work first introduces a popular deep learning model EEGNet and compares it with the traditional algorithm Filter-Bank Common Spatial Pattern (FBCSP). After that, this work considers that the 1-D convolution of EEGNet can be explained by a special Discrete Wavelet Transform (DWT), and the depthwise convolution of EEGNet is similar to the Common Spatial Pattern (CSP) algorithm. Therefore, this work improves the EEGNet by using the algorithm Temporary Constrained Sparse Group Lasso (TCSGL) to enhance its performance. The proposed model TSGL-EEGNet is tested on the BCI Competition IV 2a and BCI Competition III IIIa datasets that both are 4-classes classification MI tasks. The testing results show that the proposed model has achieved 78.96% (0.7194) average classification accuracy (kappa) on the dataset BCI Competition IV 2a, which are greater than EEGNet, C2CM, MB3DCNN, SS-MEMDBF and FBCSP, especially on insensitive subjects. The proposed model has also achieved 85.30% (0.8040) average classification accuracy (kappa) on the dataset BCI Competition III IIIa, which are greater than the EEGNet, MFTFS <italic>et al.</italic> At last, this work uses average-validation and stacking to further enhance the effect of the model. The 4-classes classification average accuracy rates reach 81.34% and 88.89%, and the kappas reach 0.7511 and 0.8519 on dataset BCI Competition IV 2a and BCI Competition III IIIa, respectively. Additionally, this work also uses the Grad-CAM to visualize the frequency and spatial features that are learned by the neural network.https://ieeexplore.ieee.org/document/9343873/Motor imageryBCICNNFBCSPtemporary constrained sparse group Lasso |
| spellingShingle | Xin Deng Boxian Zhang Nian Yu Ke Liu Kaiwei Sun Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces IEEE Access Motor imagery BCI CNN FBCSP temporary constrained sparse group Lasso |
| title | Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces |
| title_full | Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces |
| title_fullStr | Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces |
| title_full_unstemmed | Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces |
| title_short | Advanced TSGL-EEGNet for Motor Imagery EEG-Based Brain-Computer Interfaces |
| title_sort | advanced tsgl eegnet for motor imagery eeg based brain computer interfaces |
| topic | Motor imagery BCI CNN FBCSP temporary constrained sparse group Lasso |
| url | https://ieeexplore.ieee.org/document/9343873/ |
| work_keys_str_mv | AT xindeng advancedtsgleegnetformotorimageryeegbasedbraincomputerinterfaces AT boxianzhang advancedtsgleegnetformotorimageryeegbasedbraincomputerinterfaces AT nianyu advancedtsgleegnetformotorimageryeegbasedbraincomputerinterfaces AT keliu advancedtsgleegnetformotorimageryeegbasedbraincomputerinterfaces AT kaiweisun advancedtsgleegnetformotorimageryeegbasedbraincomputerinterfaces |