FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
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.
Originalsprog | Engelsk |
---|---|
Titel | 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 |
Antal sider | 5 |
Forlag | IEEE |
Publikationsdato | 2020 |
Sider | 1275-1279 |
Artikelnummer | 9283098 |
ISBN (Elektronisk) | 9781728185262 |
DOI | |
Status | Udgivet - 2020 |
Begivenhed | 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 - Toronto, Canada Varighed: 11 okt. 2020 → 14 okt. 2020 |
Konference
Konference | 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 |
---|---|
Land | Canada |
By | Toronto |
Periode | 11/10/2020 → 14/10/2020 |
Bibliografisk note
Publisher Copyright:
© 2020 IEEE.
ID: 282089155