Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency
Enhancing the performance of motor imagery-based Brain-Computer Interfaces (BCI) has been a significant goal in the BCI field. To achieve such a goal, several typical and promising techniques have been implemented, such as developing intelligent algorithms, combining features from different domains,...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914822002787 |
| _version_ | 1797951542295265280 |
|---|---|
| author | Minh Tran Duc Nguyen Nhi Yen Phan Xuan Bao Minh Pham Hiep Tran Minh Do Thu Ngoc Minh Phan Quynh Thanh Truc Nguyen Anh Hoang Lan Duong Vy Kim Huynh Bao Dinh Chau Hoang Huong Thi Thanh Ha |
| author_facet | Minh Tran Duc Nguyen Nhi Yen Phan Xuan Bao Minh Pham Hiep Tran Minh Do Thu Ngoc Minh Phan Quynh Thanh Truc Nguyen Anh Hoang Lan Duong Vy Kim Huynh Bao Dinh Chau Hoang Huong Thi Thanh Ha |
| author_sort | Minh Tran Duc Nguyen |
| collection | DOAJ |
| description | Enhancing the performance of motor imagery-based Brain-Computer Interfaces (BCI) has been a significant goal in the BCI field. To achieve such a goal, several typical and promising techniques have been implemented, such as developing intelligent algorithms, combining features from different domains, extracting subject-specific parameters, and so forth. Previous studies performing temporal segmentation often ended up with a large number of features and placed a burden on computational cost, which poses a disadvantage to online analysis. This study proposes a novel approach to utilizing short-window segments to find an optimal combination of time segments and feature extractors. Electroencephalogram data from four datasets (BCI Competition IV dataset 2a, 2b and two self-acquired datasets) were segmented into four types of the time window and had features extracted by Common Spatial Pattern and its variants, and lastly classified by Linear Discriminant Analysis. The result shows that the combination of the “2-s with 1-s overlapping” segment and Filter Bank Common Spatial Pattern yields overall accuracy of 2–6.5% (p-value <0.05), higher than other methods in comparison. In addition, the study finds that there is a negative correlation (r = −0.38) between the number of subject-specific frequency bands and the performance (p-value <0.0001). The results demonstrate that the narrower and more focus frequency range chosen, the more accurate the model can achieve. Our results indicate that the “2-s with 1-s overlapping” segment would be an ideal candidate for online BCI analysis, and the response of selected frequency bands could be an informative indicator to evaluate BCI performance. |
| first_indexed | 2024-04-10T22:32:13Z |
| format | Article |
| id | doaj.art-b6c75fee7f9a4b6e93be501066f620fe |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-04-10T22:32:13Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-b6c75fee7f9a4b6e93be501066f620fe2023-01-17T04:07:19ZengElsevierInformatics in Medicine Unlocked2352-91482023-01-0136101141Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequencyMinh Tran Duc Nguyen0Nhi Yen Phan Xuan1Bao Minh Pham2Hiep Tran Minh Do3Thu Ngoc Minh Phan4Quynh Thanh Truc Nguyen5Anh Hoang Lan Duong6Vy Kim Huynh7Bao Dinh Chau Hoang8Huong Thi Thanh Ha9Department of Biomedical Engineering, Faculty of Applied Science, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamDepartment of Biomedical Engineering, Faculty of Applied Science, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamDepartment of Biomedical Engineering, Faculty of Applied Science, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamInternational University, Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamInternational University, Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamInternational University, Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamInternational University, Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamHo Chi Minh University of Science, Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet NamPham Ngoc Thach University of Medicine, Ho Chi Minh City, 700000, Viet NamInternational University, Ho Chi Minh City, 700000, Viet Nam; Vietnam National University, Ho Chi Minh City, 700000, Viet Nam; Corresponding author. International University, Ho Chi Minh City, 700000, Viet Nam.Enhancing the performance of motor imagery-based Brain-Computer Interfaces (BCI) has been a significant goal in the BCI field. To achieve such a goal, several typical and promising techniques have been implemented, such as developing intelligent algorithms, combining features from different domains, extracting subject-specific parameters, and so forth. Previous studies performing temporal segmentation often ended up with a large number of features and placed a burden on computational cost, which poses a disadvantage to online analysis. This study proposes a novel approach to utilizing short-window segments to find an optimal combination of time segments and feature extractors. Electroencephalogram data from four datasets (BCI Competition IV dataset 2a, 2b and two self-acquired datasets) were segmented into four types of the time window and had features extracted by Common Spatial Pattern and its variants, and lastly classified by Linear Discriminant Analysis. The result shows that the combination of the “2-s with 1-s overlapping” segment and Filter Bank Common Spatial Pattern yields overall accuracy of 2–6.5% (p-value <0.05), higher than other methods in comparison. In addition, the study finds that there is a negative correlation (r = −0.38) between the number of subject-specific frequency bands and the performance (p-value <0.0001). The results demonstrate that the narrower and more focus frequency range chosen, the more accurate the model can achieve. Our results indicate that the “2-s with 1-s overlapping” segment would be an ideal candidate for online BCI analysis, and the response of selected frequency bands could be an informative indicator to evaluate BCI performance.http://www.sciencedirect.com/science/article/pii/S2352914822002787Common spatial patternFilter banksTemporal segmentationSubject-specificMotor imageryOnline BCI |
| spellingShingle | Minh Tran Duc Nguyen Nhi Yen Phan Xuan Bao Minh Pham Hiep Tran Minh Do Thu Ngoc Minh Phan Quynh Thanh Truc Nguyen Anh Hoang Lan Duong Vy Kim Huynh Bao Dinh Chau Hoang Huong Thi Thanh Ha Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency Informatics in Medicine Unlocked Common spatial pattern Filter banks Temporal segmentation Subject-specific Motor imagery Online BCI |
| title | Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency |
| title_full | Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency |
| title_fullStr | Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency |
| title_full_unstemmed | Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency |
| title_short | Optimize temporal configuration for motor imagery-based multiclass performance and its relationship with subject-specific frequency |
| title_sort | optimize temporal configuration for motor imagery based multiclass performance and its relationship with subject specific frequency |
| topic | Common spatial pattern Filter banks Temporal segmentation Subject-specific Motor imagery Online BCI |
| url | http://www.sciencedirect.com/science/article/pii/S2352914822002787 |
| work_keys_str_mv | AT minhtranducnguyen optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT nhiyenphanxuan optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT baominhpham optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT hieptranminhdo optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT thungocminhphan optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT quynhthanhtrucnguyen optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT anhhoanglanduong optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT vykimhuynh optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT baodinhchauhoang optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency AT huongthithanhha optimizetemporalconfigurationformotorimagerybasedmulticlassperformanceanditsrelationshipwithsubjectspecificfrequency |