Current Source Density Estimation Enhances the Performance of Motor-Imagery-Related Brain–Computer Interface
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1223
- Type
- D - Journal article
- DOI
-
10.1109/TNSRE.2017.2726779
- Title of journal
- IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Article number
- -
- First page
- 2461
- Volume
- 25
- Issue
- 12
- ISSN
- 1534-4320
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
3
- Research group(s)
-
B - Brain Computer Interfaces and Neural Engineering (BCI-NE)
- Citation count
- 15
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Handling non-stationarity in EEG is a major-challenge in using EEG-based BCI systems. We proposed a completely new, robustly tested approach, the Current Source Density Estimation method, which provides a significant improvement of 3.02% and 5.59% across six binary classification tasks and four-class classification task for motor imagery, respectively. The paper is significant because our approach outperforms state-of-the-art such as Laplacian and CR and is also applicable to MEG-based BCI systems. Citations and downloads indicate that this work, published in IEEE-TNSRE, a leading journal in the topic, has been warmly accepted by the BCI-community. Results underpin our current work.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -