A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces
The brain–computer interface (BCI) is used to understand brain activities and external bodies with the help of the motor imagery (MI). As of today, the classification results for EEG 4 class BCI competition dataset have been improved to provide better classification accuracy of the brain computer in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/15/5860 |
| _version_ | 1797432627569885184 |
|---|---|
| author | Hojong Choi Junghun Park Yeon-Mo Yang |
| author_facet | Hojong Choi Junghun Park Yeon-Mo Yang |
| author_sort | Hojong Choi |
| collection | DOAJ |
| description | The brain–computer interface (BCI) is used to understand brain activities and external bodies with the help of the motor imagery (MI). As of today, the classification results for EEG 4 class BCI competition dataset have been improved to provide better classification accuracy of the brain computer interface systems (BCIs). Based on this observation, a novel quick-response eigenface analysis (QR-EFA) scheme for motor imagery is proposed to improve the classification accuracy for BCIs. Thus, we considered BCI signals in standardized and sharable quick response (QR) image domain; then, we systematically combined EFA and a convolution neural network (CNN) to classify the neuro images. To overcome a non-stationary BCI dataset available and non-ergodic characteristics, we utilized an effective neuro data augmentation in the training phase. For the ultimate improvements in classification performance, QR-EFA maximizes the similarities existing in the domain-, trial-, and subject-wise directions. To validate and verify the proposed scheme, we performed an experiment on the BCI dataset. Specifically, the scheme is intended to provide a higher classification output in classification accuracy performance for the BCI competition 4 dataset 2a (C4D2a_4C) and BCI competition 3 dataset 3a (C3D3a_4C). The experimental results confirm that the newly proposed QR-EFA method outperforms the previous the published results, specifically from 85.4% to 97.87% ± 0.75 for C4D2a_4C and 88.21% ± 6.02 for C3D3a_4C. Therefore, the proposed QR-EFA could be a highly reliable and constructive framework for one of the MI classification solutions for BCI applications. |
| first_indexed | 2024-03-09T10:04:21Z |
| format | Article |
| id | doaj.art-53280119844641ccb3940eb8474b1e43 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T10:04:21Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-53280119844641ccb3940eb8474b1e432023-12-01T23:10:45ZengMDPI AGSensors1424-82202022-08-012215586010.3390/s22155860A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer InterfacesHojong Choi0Junghun Park1Yeon-Mo Yang2Department of Electronic Engineering, Gachon University, 1342 Seongnam-daero, Seongnam 13306, KoreaSchool of Electronic Engineering, Kumoh National Institute of Technology, 61 Daehak-ro, Gumi 39177, KoreaSchool of Electronic Engineering, Kumoh National Institute of Technology, 61 Daehak-ro, Gumi 39177, KoreaThe brain–computer interface (BCI) is used to understand brain activities and external bodies with the help of the motor imagery (MI). As of today, the classification results for EEG 4 class BCI competition dataset have been improved to provide better classification accuracy of the brain computer interface systems (BCIs). Based on this observation, a novel quick-response eigenface analysis (QR-EFA) scheme for motor imagery is proposed to improve the classification accuracy for BCIs. Thus, we considered BCI signals in standardized and sharable quick response (QR) image domain; then, we systematically combined EFA and a convolution neural network (CNN) to classify the neuro images. To overcome a non-stationary BCI dataset available and non-ergodic characteristics, we utilized an effective neuro data augmentation in the training phase. For the ultimate improvements in classification performance, QR-EFA maximizes the similarities existing in the domain-, trial-, and subject-wise directions. To validate and verify the proposed scheme, we performed an experiment on the BCI dataset. Specifically, the scheme is intended to provide a higher classification output in classification accuracy performance for the BCI competition 4 dataset 2a (C4D2a_4C) and BCI competition 3 dataset 3a (C3D3a_4C). The experimental results confirm that the newly proposed QR-EFA method outperforms the previous the published results, specifically from 85.4% to 97.87% ± 0.75 for C4D2a_4C and 88.21% ± 6.02 for C3D3a_4C. Therefore, the proposed QR-EFA could be a highly reliable and constructive framework for one of the MI classification solutions for BCI applications.https://www.mdpi.com/1424-8220/22/15/5860motor imagery classificationeigenface analysisquick response neuro imagesimage data augmentationstandardized and sharable quick response eigenfaces |
| spellingShingle | Hojong Choi Junghun Park Yeon-Mo Yang A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces Sensors motor imagery classification eigenface analysis quick response neuro images image data augmentation standardized and sharable quick response eigenfaces |
| title | A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces |
| title_full | A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces |
| title_fullStr | A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces |
| title_full_unstemmed | A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces |
| title_short | A Novel Quick-Response Eigenface Analysis Scheme for Brain–Computer Interfaces |
| title_sort | novel quick response eigenface analysis scheme for brain computer interfaces |
| topic | motor imagery classification eigenface analysis quick response neuro images image data augmentation standardized and sharable quick response eigenfaces |
| url | https://www.mdpi.com/1424-8220/22/15/5860 |
| work_keys_str_mv | AT hojongchoi anovelquickresponseeigenfaceanalysisschemeforbraincomputerinterfaces AT junghunpark anovelquickresponseeigenfaceanalysisschemeforbraincomputerinterfaces AT yeonmoyang anovelquickresponseeigenfaceanalysisschemeforbraincomputerinterfaces AT hojongchoi novelquickresponseeigenfaceanalysisschemeforbraincomputerinterfaces AT junghunpark novelquickresponseeigenfaceanalysisschemeforbraincomputerinterfaces AT yeonmoyang novelquickresponseeigenfaceanalysisschemeforbraincomputerinterfaces |