FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification : A Machine Learning Approach. / Das, Rig; Lopez, Paula S.; Ahmed Khan, Muhammad; Iversen, Helle K.; Puthusserypady, Sadasivan.
2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. IEEE, 2020. p. 1275-1279 9283098.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification
T2 - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
AU - Das, Rig
AU - Lopez, Paula S.
AU - Ahmed Khan, Muhammad
AU - Iversen, Helle K.
AU - Puthusserypady, Sadasivan
N1 - Funding Information: ACKNOWLEDGMENT We gratefully acknowledge the support of NVIDIA® Corporation, for providing the Titan X™ GPU that is used for this research. Publisher Copyright: © 2020 IEEE.
PY - 2020
Y1 - 2020
N2 - Classification of non-stationary electroencephalogram (EEG) data are of utmost importance for brain-computer interface (BCI) technology. This paper proposes a robust multiclass motor imagery (MI) BCI data classification technique. It is based on filter bank common spatial patterns (FBCSP) and AdaBoost classification technique. The method is tested on the 4-class MI BCI competition IV dataset 2a and the results show superior performance compared to the current state-of-the-art performances. This paper also analyzes different frequency sub-bands for the MI EEG data, in order to find the best sub-band which contains the most significant features for distinguishing different MI tasks.
AB - Classification of non-stationary electroencephalogram (EEG) data are of utmost importance for brain-computer interface (BCI) technology. This paper proposes a robust multiclass motor imagery (MI) BCI data classification technique. It is based on filter bank common spatial patterns (FBCSP) and AdaBoost classification technique. The method is tested on the 4-class MI BCI competition IV dataset 2a and the results show superior performance compared to the current state-of-the-art performances. This paper also analyzes different frequency sub-bands for the MI EEG data, in order to find the best sub-band which contains the most significant features for distinguishing different MI tasks.
KW - Adaptive boosting (AdaBoost)
KW - Brain computer interface (BCI)
KW - filter-bank common spatial patterns (FBCSP)
KW - motor imagery (MI)
U2 - 10.1109/SMC42975.2020.9283098
DO - 10.1109/SMC42975.2020.9283098
M3 - Article in proceedings
AN - SCOPUS:85098885506
SP - 1275
EP - 1279
BT - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PB - IEEE
Y2 - 11 October 2020 through 14 October 2020
ER -
ID: 282089155