Motor Imagery Classification Based on Bilinear Sub-Manifold Learning of Symmetric Positive-Definite Matrices
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2545
- Type
- D - Journal article
- DOI
-
10.1109/TNSRE.2016.2587939
- Title of journal
- IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Article number
- -
- First page
- 504
- Volume
- 25
- Issue
- 6
- ISSN
- 1534-4320
- Open access status
- Deposit exception
- Month of publication
- July
- Year of publication
- 2016
- 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
- No
- Number of additional authors
-
4
- Research group(s)
-
C - Machine Learning
- Citation count
- 25
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a novel method for classifying motor imagery EEG signals by exploiting Riemannian geometry that significantly improves speed (5x), accuracy and robustness compared to earlier methods. It has received growing attention and increasing recognition in the brain-computer interfaces (BCI) community, with citations from top journals such as NeuroImage, TNNLS, TNSRE, and TIE. It is considered state-of-the-art development in a recent review in the official journal of the BCI society (Congedo, Brain Comp Interfaces 2017, doi.org/10.1080/2326263X.2017.1297192).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -