An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System
Brain-computer interface (BCI) is an evolving technology having huge potential for rehabilitation of patients suffering from disorders of the nervous system, besides many other nonmedical applications. Multichannel electroencephalography (EEG) is widely used to provide input signals to a BCI syste...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Koya University
2022-05-01
|
| Series: | ARO-The Scientific Journal of Koya University |
| Subjects: | |
| Online Access: | https://aro.koyauniversity.org/index.php/aro/article/view/926 |
| _version_ | 1797720936843051008 |
|---|---|
| author | Navtej S. Ghumman Balkrishan Jindal |
| author_facet | Navtej S. Ghumman Balkrishan Jindal |
| author_sort | Navtej S. Ghumman |
| collection | DOAJ |
| description |
Brain-computer interface (BCI) is an evolving technology having huge potential for rehabilitation of patients suffering from disorders of the nervous system, besides many other nonmedical applications. Multichannel electroencephalography (EEG) is widely used to provide input signals to a BCI system. Significant research in methodology employed to implement different stages of BCI system, has led to discovery of new issues and challenges. The raw EEG data includes artifacts from environmental and physiological sources, which is eliminated in preprocessing phase of BCI system. It is then followed by a feature extraction stage to isolate a few relevant features for further classification to a particular motor imagery (MI) activity. A feature extraction approach based on spectrally weighted common spatial pattern (SWCSP) is proposed in this paper to improve overall accuracy of a BCI system. The reported literature uses SWCSP for feature extraction, as it has outperformed other techniques. The proposed approach enhances its performance by optimizing its parameters. The independent component analysis (ICA) method is used for detection and removal of irrelevant data, while linear discriminant analysis (LDA) is used as a classifier. The proposed approach is executed on benchmark data-set 2a of BCI competition IV. It yielded classification accuracy of 70.6% across nine subjects, which is higher than all the reported approaches.
|
| first_indexed | 2024-03-12T09:26:41Z |
| format | Article |
| id | doaj.art-c24422ea9ae0447b840f176ccd295fe0 |
| institution | Directory Open Access Journal |
| issn | 2410-9355 2307-549X |
| language | English |
| last_indexed | 2024-03-12T09:26:41Z |
| publishDate | 2022-05-01 |
| publisher | Koya University |
| record_format | Article |
| series | ARO-The Scientific Journal of Koya University |
| spelling | doaj.art-c24422ea9ae0447b840f176ccd295fe02023-09-02T14:11:54ZengKoya UniversityARO-The Scientific Journal of Koya University2410-93552307-549X2022-05-0110110.14500/aro.10926An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI SystemNavtej S. Ghumman0Balkrishan Jindal1Department of Computer Science and Engineering, Punjabi University Patiala, Punjab, IndiaDepartment of Computer Engineering, YCoE, Punjabi University Guru Kashi Campus Talwandi Sabo, Punjab, India Brain-computer interface (BCI) is an evolving technology having huge potential for rehabilitation of patients suffering from disorders of the nervous system, besides many other nonmedical applications. Multichannel electroencephalography (EEG) is widely used to provide input signals to a BCI system. Significant research in methodology employed to implement different stages of BCI system, has led to discovery of new issues and challenges. The raw EEG data includes artifacts from environmental and physiological sources, which is eliminated in preprocessing phase of BCI system. It is then followed by a feature extraction stage to isolate a few relevant features for further classification to a particular motor imagery (MI) activity. A feature extraction approach based on spectrally weighted common spatial pattern (SWCSP) is proposed in this paper to improve overall accuracy of a BCI system. The reported literature uses SWCSP for feature extraction, as it has outperformed other techniques. The proposed approach enhances its performance by optimizing its parameters. The independent component analysis (ICA) method is used for detection and removal of irrelevant data, while linear discriminant analysis (LDA) is used as a classifier. The proposed approach is executed on benchmark data-set 2a of BCI competition IV. It yielded classification accuracy of 70.6% across nine subjects, which is higher than all the reported approaches. https://aro.koyauniversity.org/index.php/aro/article/view/926Brain-computer interfaceCommon spatial patternElectroencephalogramFeature extractionMotor imagery |
| spellingShingle | Navtej S. Ghumman Balkrishan Jindal An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System ARO-The Scientific Journal of Koya University Brain-computer interface Common spatial pattern Electroencephalogram Feature extraction Motor imagery |
| title | An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System |
| title_full | An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System |
| title_fullStr | An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System |
| title_full_unstemmed | An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System |
| title_short | An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System |
| title_sort | optimized swcsp technique for feature extraction in eeg based bci system |
| topic | Brain-computer interface Common spatial pattern Electroencephalogram Feature extraction Motor imagery |
| url | https://aro.koyauniversity.org/index.php/aro/article/view/926 |
| work_keys_str_mv | AT navtejsghumman anoptimizedswcsptechniqueforfeatureextractionineegbasedbcisystem AT balkrishanjindal anoptimizedswcsptechniqueforfeatureextractionineegbasedbcisystem AT navtejsghumman optimizedswcsptechniqueforfeatureextractionineegbasedbcisystem AT balkrishanjindal optimizedswcsptechniqueforfeatureextractionineegbasedbcisystem |