FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach

Rig Das, Paula Sánchez López , Muhammad Ahmed Khan, Helle K. Iversen, Sadasivan Puthusserypady

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

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 subbands for the MI EEG data, in order to find the best sub-band which contains the most significant features for distinguishing different MI tasks.
Original languageEnglish
Title of host publicationProceedings of 2020 IEEE International Conference on Systems, Man, and Cybernetics
PublisherIEEE
Publication date2020
Pages1275-1279
ISBN (Print)978-1-7281-8526-2
DOIs
Publication statusPublished - 2020
Event2020 IEEE International Conference on Systems, Man, and Cybernetics - Virtual event, Toronto, Canada
Duration: 11 Oct 202014 Oct 2020
http://smc2020.org/

Conference

Conference2020 IEEE International Conference on Systems, Man, and Cybernetics
LocationVirtual event
CountryCanada
CityToronto
Period11/10/202014/10/2020
Internet address

Keywords

  • Brain computer interface (BCI)
  • Filter-bank common spatial patterns (FBCSP)
  • Motor imagery (MI)
  • Adaptive boosting (AdaBoost)

Fingerprint Dive into the research topics of 'FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach'. Together they form a unique fingerprint.

Cite this