Song, YoungJae and Sepulveda, Francisco (2018) A Novel Technique for Selecting EMG-Contaminated EEG Channels in Self-Paced Brain-Computer Interface Task Onset. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26 (7). pp. 1353-1362. DOI https://doi.org/10.1109/TNSRE.2018.2847316
Song, YoungJae and Sepulveda, Francisco (2018) A Novel Technique for Selecting EMG-Contaminated EEG Channels in Self-Paced Brain-Computer Interface Task Onset. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26 (7). pp. 1353-1362. DOI https://doi.org/10.1109/TNSRE.2018.2847316
Song, YoungJae and Sepulveda, Francisco (2018) A Novel Technique for Selecting EMG-Contaminated EEG Channels in Self-Paced Brain-Computer Interface Task Onset. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26 (7). pp. 1353-1362. DOI https://doi.org/10.1109/TNSRE.2018.2847316
Abstract
Electromyography artefacts are a well-known problem in Electroencephalography studies (BCIs, brain mapping, and clinical areas). Blind source separation (BSS) techniques are commonly used to handle artefacts. However, these may remove not only EMG artefacts but also some useful EEG sources. To reduce this useful information loss, we propose a new technique for statistically selecting EEG channels that are contaminated with class-dependent EMG (henceforth called EMG-CCh). Methods: The EMG-CCh are selected based on the correlation between EEG and facial EMG channels. They were compared (using a Wilcoxon test) to determine whether the artefacts played a significant role in class separation. To ensure that promising results are not due to weak EMG removal, reliability tests were done. Results: In our data set, the comparison results between BSS artefact removal applied in two ways, to all channels and only to EMG-CCh, showed that ICA, PCA and BSS-CCA can yield significantly better (p<0.05) class separation with the proposed method (79% of the cases for ICA, 53% for PCA and 11% for BSS-CCA). With BCI competition data, we saw improvement in 60% of the cases for ICA and BSS-CCA. Conclusion: The simple method proposed in this paper showed improvement in class separation with both our data and the BCI competition data. Significance: There are no existing methods for removing EMG artefacts based on the correlation between EEG and EMG channels. Also, the EMG-CCh selection can be used on its own or it can be combined with pre-existing artefact handling methods. For these reasons, we believe this method can be useful for other EEG studies.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Correlation; Electroencephalography; Electromyography; Electrooculography; Integrated circuits; Principal component analysis; Task analysis; Artefact removal; Blind source separation; Brain-Computer interface; CCA; EEG; EMG-CCh selection; EMG/EOG artefacts; ICA; PCA |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 27 Jun 2018 10:42 |
Last Modified: | 16 May 2024 19:28 |
URI: | http://repository.essex.ac.uk/id/eprint/22329 |
Available files
Filename: 08385222.pdf