An Efficient Multi-Class MI Based BCI Scheme Using Statistical Fusion Techniques of Classifiers
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
An Efficient Multi-Class MI Based BCI Scheme Using Statistical Fusion Techniques of Classifiers. / Lopez, Paula Sanchez; Iversen, Helle K.; Puthusserypady, Sadasivan.
Proceedings of the TENCON 2019: Technology, Knowledge, and Society. IEEE, 2019. p. 378-382 8929345 (IEEE Region 10 Annual International Conference, Proceedings/TENCON, Vol. 2019-October).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - An Efficient Multi-Class MI Based BCI Scheme Using Statistical Fusion Techniques of Classifiers
AU - Lopez, Paula Sanchez
AU - Iversen, Helle K.
AU - Puthusserypady, Sadasivan
PY - 2019
Y1 - 2019
N2 - An efficient implementation of a multi-class motor imagery (MI) brain computer interface (BCI) classification scheme is presented in this work. The proposed method uses the common spatial pattern (CSP) and filter bank CSP (FBCSP) algorithms, with both one versus all (OVA) and one versus one (OVO) approach for multi-class extension. Mutual information (MInf) based feature selection algorithm has been used to obtain the features to train different linear discriminant analysis (LDA) classifiers. To improve the performance, the outputs of these classifiers are combined using two statistical methods: the mode of the OVA and OVO classifiers, and the more sophisticated Dempster-Shafer (DS) theory. The method has been evaluated on the 4-class MI dataset (BCI competition IV 2a), and the results showed that it has outperformed the winner of the competition (maximum kappa value of 0.593 vs 0.569). The proposed method proved the benefits of combining classifiers with appropriate techniques.
AB - An efficient implementation of a multi-class motor imagery (MI) brain computer interface (BCI) classification scheme is presented in this work. The proposed method uses the common spatial pattern (CSP) and filter bank CSP (FBCSP) algorithms, with both one versus all (OVA) and one versus one (OVO) approach for multi-class extension. Mutual information (MInf) based feature selection algorithm has been used to obtain the features to train different linear discriminant analysis (LDA) classifiers. To improve the performance, the outputs of these classifiers are combined using two statistical methods: the mode of the OVA and OVO classifiers, and the more sophisticated Dempster-Shafer (DS) theory. The method has been evaluated on the 4-class MI dataset (BCI competition IV 2a), and the results showed that it has outperformed the winner of the competition (maximum kappa value of 0.593 vs 0.569). The proposed method proved the benefits of combining classifiers with appropriate techniques.
KW - Brain Computer Interface
KW - Common Spatial Pattern
KW - Dempster-Shafer theory
KW - Multi-class Motor Imagery
KW - Mutual Information
U2 - 10.1109/TENCON.2019.8929345
DO - 10.1109/TENCON.2019.8929345
M3 - Article in proceedings
AN - SCOPUS:85077674580
T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON
SP - 378
EP - 382
BT - Proceedings of the TENCON 2019
PB - IEEE
T2 - 2019 IEEE Region 10 Conference: Technology, Knowledge, and Society, TENCON 2019
Y2 - 17 October 2019 through 20 October 2019
ER -
ID: 241597271