Kernel learning over the manifold of symmetric positive definite matrices for dimensionality reduction in a BCI application
- Submitting institution
-
Staffordshire University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 6793
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2015.11.065
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 152-160
- Volume
- 179
- Issue
- -
- ISSN
- 0925-2312
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2016
- URL
-
https://www.sciencedirect.com/science/article/abs/pii/S092523121501872X?via%3Dihub
- 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
- No
- Number of additional authors
-
0
- Research group(s)
-
B - Centre for Smart Systems, AI and Cybersecurity (CSSAIC)
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The reliability of electroencephalogram (EEG)-based diagnosis is crucial as a major requirement in actual clinical practice. By reducing the dimensionality of the problem, the approach proposed in this paper demonstrated increased accuracy of classification compared to existing methods. The dimensionality reduction in a BCI application aspects of the paper were recognized in a Keynote talk at the University of Littoral, France in 2019 (https://www-lisic.univ-littoral.fr/article396.html).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -