Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE

Abstract: 

The ubiquitous presence of non-stationarities in the EEG signals significantly perturb the feature distribution thus deteriorating the performance of Brain Computer Interface. In this work, a novel method is proposed based on Joint Approximate Diagonalization (JAD) to optimize stationarity for multiclass motor imagery Brain Computer Interface (BCI) in an information theoretic framework. Specifically, in the proposed method, we estimate the subspace which optimizes the discriminability between the classes and simultaneously preserve stationarity within the motor imagery classes. We determine the subspace for the proposed approach through optimization using gradient descent on an orthogonal manifold. The performance of the proposed stationarity enforcing algorithm is compared to that of baseline One-Versus-Rest (OVR)-CSP and JAD on publicly available BCI competition IV dataset IIa. Results show that an improvement in average classification accuracies across the subjects over the baseline algorithms and thus essence of alleviating within session non-stationarities.

up
0 users have voted:

Paper Details

Authors:
satyam kumar, tharun kumar reddy, vipul arora, laxmidhar behera
Submitted On:
14 May 2020 - 12:45pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Tharun kumar reddy
Paper Code:
2541
Document Year:
2020
Cite

Document Files

ICASSP2020_ppt_2541paperId_shortVersionPPT.pdf

(17)

Subscribe

[1] satyam kumar, tharun kumar reddy, vipul arora, laxmidhar behera, "FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5315. Accessed: Jul. 12, 2020.
@article{5315-20,
url = {http://sigport.org/5315},
author = {satyam kumar; tharun kumar reddy; vipul arora; laxmidhar behera },
publisher = {IEEE SigPort},
title = {FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE},
year = {2020} }
TY - EJOUR
T1 - FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE
AU - satyam kumar; tharun kumar reddy; vipul arora; laxmidhar behera
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5315
ER -
satyam kumar, tharun kumar reddy, vipul arora, laxmidhar behera. (2020). FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE. IEEE SigPort. http://sigport.org/5315
satyam kumar, tharun kumar reddy, vipul arora, laxmidhar behera, 2020. FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE. Available at: http://sigport.org/5315.
satyam kumar, tharun kumar reddy, vipul arora, laxmidhar behera. (2020). "FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE." Web.
1. satyam kumar, tharun kumar reddy, vipul arora, laxmidhar behera. FORMULATING DIVERGENCE FRAMEWORK FOR MULTICLASS MOTOR IMAGERY EEG BRAIN COMPUTER INTERFACE [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5315