Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI

Raheleh Mohammadi, Ali Mahloojifar, Damien Coyle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A major challenge for Brain Computer Interface systems (BCIs) is dealing with non-stationarity in the EEG signal. There are two types of EEG non-stationarities 1) long-term changes related to fatigue, changes in recording conditions or effects of feedback training which is addressed in classification step and 2) short-term changes related to different mental activities and drifts in slow cortical potentials which can be addressed in the feature extraction step. In this paper we use a covariate shift minimization (CSM) method to alleviate the shortterm (single trial) effects of EEG non-stationarity to improve the performance of self-paced BCIs in detecting foot movement from the continuous EEG signal. The results of applying this unsupervised covariate shift minimization with two different classifiers, linear discriminant analysis (LDA) and probabilistic classification vector machines (PCVMs) along with two different filtering methods (constant bandwidth and constant-Q filters) show the considerable improvement in system performance.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages101-106
Number of pages6
Publication statusPublished - 2013
Event2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB) - Singapore
Duration: 1 Jan 2013 → …

Conference

Conference2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB)
Period1/01/13 → …

Fingerprint

Electroencephalography
Brain computer interface
Discriminant analysis
Feature extraction
Classifiers
Fatigue of materials
Feedback
Bandwidth

Cite this

Mohammadi, R., Mahloojifar, A., & Coyle, D. (2013). Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI. In Unknown Host Publication (pp. 101-106)
Mohammadi, Raheleh ; Mahloojifar, Ali ; Coyle, Damien. / Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI. Unknown Host Publication. 2013. pp. 101-106
@inproceedings{2a171914df6e4dbd8e70d4e1ef84baeb,
title = "Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI",
abstract = "A major challenge for Brain Computer Interface systems (BCIs) is dealing with non-stationarity in the EEG signal. There are two types of EEG non-stationarities 1) long-term changes related to fatigue, changes in recording conditions or effects of feedback training which is addressed in classification step and 2) short-term changes related to different mental activities and drifts in slow cortical potentials which can be addressed in the feature extraction step. In this paper we use a covariate shift minimization (CSM) method to alleviate the shortterm (single trial) effects of EEG non-stationarity to improve the performance of self-paced BCIs in detecting foot movement from the continuous EEG signal. The results of applying this unsupervised covariate shift minimization with two different classifiers, linear discriminant analysis (LDA) and probabilistic classification vector machines (PCVMs) along with two different filtering methods (constant bandwidth and constant-Q filters) show the considerable improvement in system performance.",
author = "Raheleh Mohammadi and Ali Mahloojifar and Damien Coyle",
year = "2013",
language = "English",
pages = "101--106",
booktitle = "Unknown Host Publication",

}

Mohammadi, R, Mahloojifar, A & Coyle, D 2013, Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI. in Unknown Host Publication. pp. 101-106, 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), 1/01/13.

Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI. / Mohammadi, Raheleh; Mahloojifar, Ali; Coyle, Damien.

Unknown Host Publication. 2013. p. 101-106.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI

AU - Mohammadi, Raheleh

AU - Mahloojifar, Ali

AU - Coyle, Damien

PY - 2013

Y1 - 2013

N2 - A major challenge for Brain Computer Interface systems (BCIs) is dealing with non-stationarity in the EEG signal. There are two types of EEG non-stationarities 1) long-term changes related to fatigue, changes in recording conditions or effects of feedback training which is addressed in classification step and 2) short-term changes related to different mental activities and drifts in slow cortical potentials which can be addressed in the feature extraction step. In this paper we use a covariate shift minimization (CSM) method to alleviate the shortterm (single trial) effects of EEG non-stationarity to improve the performance of self-paced BCIs in detecting foot movement from the continuous EEG signal. The results of applying this unsupervised covariate shift minimization with two different classifiers, linear discriminant analysis (LDA) and probabilistic classification vector machines (PCVMs) along with two different filtering methods (constant bandwidth and constant-Q filters) show the considerable improvement in system performance.

AB - A major challenge for Brain Computer Interface systems (BCIs) is dealing with non-stationarity in the EEG signal. There are two types of EEG non-stationarities 1) long-term changes related to fatigue, changes in recording conditions or effects of feedback training which is addressed in classification step and 2) short-term changes related to different mental activities and drifts in slow cortical potentials which can be addressed in the feature extraction step. In this paper we use a covariate shift minimization (CSM) method to alleviate the shortterm (single trial) effects of EEG non-stationarity to improve the performance of self-paced BCIs in detecting foot movement from the continuous EEG signal. The results of applying this unsupervised covariate shift minimization with two different classifiers, linear discriminant analysis (LDA) and probabilistic classification vector machines (PCVMs) along with two different filtering methods (constant bandwidth and constant-Q filters) show the considerable improvement in system performance.

M3 - Conference contribution

SP - 101

EP - 106

BT - Unknown Host Publication

ER -

Mohammadi R, Mahloojifar A, Coyle D. Unsupervised Short-term Covariate Shift Minimization for Self-paced BCI. In Unknown Host Publication. 2013. p. 101-106