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

doi:10.1109/SMC42975.2020.9283098

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

Technical University of Denmark
Copenhagen University Hospital Herlev and Gentofte

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-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 language	English
Title of host publication	Proceedings of 2020 IEEE International Conference on Systems, Man, and Cybernetics
Publisher	IEEE
Publication date	2020
Pages	1275-1279
ISBN (Print)	978-1-7281-8526-2
DOIs	https://doi.org/10.1109/SMC42975.2020.9283098
Publication status	Published - 2020
Event	2020 IEEE International Conference on Systems, Man, and Cybernetics - Virtual event, Toronto, Canada Duration: 11 Oct 2020 → 14 Oct 2020 http://smc2020.org/

Conference

Conference	2020 IEEE International Conference on Systems, Man, and Cybernetics
Location	Virtual event
Country/Territory	Canada
City	Toronto
Period	11/10/2020 → 14/10/2020
Internet address	http://smc2020.org/

Keywords

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

Access to Document

10.1109/SMC42975.2020.9283098

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{a8b052b8f4864814bc956298f65ade1a,

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

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.",

keywords = "Brain computer interface (BCI), Filter-bank common spatial patterns (FBCSP), Motor imagery (MI), Adaptive boosting (AdaBoost)",

author = "Rig Das and L{\'o}pez, \{Paula S{\'a}nchez\} and Khan, \{Muhammad Ahmed\} and Iversen, \{Helle K.\} and Sadasivan Puthusserypady",

year = "2020",

doi = "10.1109/SMC42975.2020.9283098",

language = "English",

isbn = "978-1-7281-8526-2",

pages = "1275--1279",

booktitle = "Proceedings of 2020 IEEE International Conference on Systems, Man, and Cybernetics",

publisher = "IEEE",

address = "United States",

note = "2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 ; Conference date: 11-10-2020 Through 14-10-2020",

url = "http://smc2020.org/",

}

Das, R, López , PS, Khan, MA, Iversen, HK & Puthusserypady, S 2020, FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach. in Proceedings of 2020 IEEE International Conference on Systems, Man, and Cybernetics. IEEE, pp. 1275-1279, 2020 IEEE International Conference on Systems, Man, and Cybernetics, Toronto, Ontario, Canada, 11/10/2020. https://doi.org/10.1109/SMC42975.2020.9283098

FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach. / Das, Rig; López , Paula Sánchez; Khan, Muhammad Ahmed et al.
Proceedings of 2020 IEEE International Conference on Systems, Man, and Cybernetics. IEEE, 2020. p. 1275-1279.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - FBCSP and Adaptive Boosting for Multiclass Motor Imagery BCI Data Classification: A Machine Learning Approach

AU - Das, Rig

AU - López , Paula Sánchez

AU - Khan, Muhammad Ahmed

AU - Iversen, Helle K.

AU - Puthusserypady, Sadasivan

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 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.

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 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.

KW - Brain computer interface (BCI)

KW - Filter-bank common spatial patterns (FBCSP)

KW - Motor imagery (MI)

KW - Adaptive boosting (AdaBoost)

U2 - 10.1109/SMC42975.2020.9283098

DO - 10.1109/SMC42975.2020.9283098

M3 - Article in proceedings

SN - 978-1-7281-8526-2

SP - 1275

EP - 1279

BT - Proceedings of 2020 IEEE International Conference on Systems, Man, and Cybernetics

PB - IEEE

T2 - 2020 IEEE International Conference on Systems, Man, and Cybernetics

Y2 - 11 October 2020 through 14 October 2020

ER -

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

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this