Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP

Raheleh Mohammadi, Ali Mahloojifar, DH Coyle

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

Abstract

Electroencephalogram (EEG) signals used in brain computer interfaces (BCIs) change over time, both within a single session and between sessions. Factors such as change in strategy by the user, sensorimotor learning, user fatigue, small differences in electrode position and muscular activity result in nonstationary EEG dynamics. Dealing with these characteristics when transferring from the calibration to a feedback session is a challenging but critical issue in BCI applications. To cope with this problem, a framework based on constant-Q filter bank Common Spatial Patterns (FBCSP) and Linear Discriminant Analysis (LDA) is proposed. This framework has been applied on dataset IVc from the BCI Competition III. Results show that the proposed method compares favorably with an adaptive framework such as covariate shift adaptation in tackling the nonstationarity in BCIs.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages5
Volume2012
Publication statusPublished - 2012
EventThe 19th Iranian Conference on Biomedical Engineering (ICBME) - Iran
Duration: 1 Jan 2012 → …

Conference

ConferenceThe 19th Iranian Conference on Biomedical Engineering (ICBME)
Period1/01/12 → …

Fingerprint

Brain computer interface
Filter banks
Electroencephalography
Discriminant analysis
Fatigue of materials
Calibration
Feedback
Electrodes

Cite this

Mohammadi, R., Mahloojifar, A., & Coyle, DH. (2012). Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP. In Unknown Host Publication (Vol. 2012)
Mohammadi, Raheleh ; Mahloojifar, Ali ; Coyle, DH. / Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP. Unknown Host Publication. Vol. 2012 2012.
@inproceedings{4c34a7cc7d72406ba09c4a379ea6075d,
title = "Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP",
abstract = "Electroencephalogram (EEG) signals used in brain computer interfaces (BCIs) change over time, both within a single session and between sessions. Factors such as change in strategy by the user, sensorimotor learning, user fatigue, small differences in electrode position and muscular activity result in nonstationary EEG dynamics. Dealing with these characteristics when transferring from the calibration to a feedback session is a challenging but critical issue in BCI applications. To cope with this problem, a framework based on constant-Q filter bank Common Spatial Patterns (FBCSP) and Linear Discriminant Analysis (LDA) is proposed. This framework has been applied on dataset IVc from the BCI Competition III. Results show that the proposed method compares favorably with an adaptive framework such as covariate shift adaptation in tackling the nonstationarity in BCIs.",
author = "Raheleh Mohammadi and Ali Mahloojifar and DH Coyle",
year = "2012",
language = "English",
volume = "2012",
booktitle = "Unknown Host Publication",

}

Mohammadi, R, Mahloojifar, A & Coyle, DH 2012, Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP. in Unknown Host Publication. vol. 2012, The 19th Iranian Conference on Biomedical Engineering (ICBME), 1/01/12.

Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP. / Mohammadi, Raheleh; Mahloojifar, Ali; Coyle, DH.

Unknown Host Publication. Vol. 2012 2012.

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

TY - GEN

T1 - Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP

AU - Mohammadi, Raheleh

AU - Mahloojifar, Ali

AU - Coyle, DH

PY - 2012

Y1 - 2012

N2 - Electroencephalogram (EEG) signals used in brain computer interfaces (BCIs) change over time, both within a single session and between sessions. Factors such as change in strategy by the user, sensorimotor learning, user fatigue, small differences in electrode position and muscular activity result in nonstationary EEG dynamics. Dealing with these characteristics when transferring from the calibration to a feedback session is a challenging but critical issue in BCI applications. To cope with this problem, a framework based on constant-Q filter bank Common Spatial Patterns (FBCSP) and Linear Discriminant Analysis (LDA) is proposed. This framework has been applied on dataset IVc from the BCI Competition III. Results show that the proposed method compares favorably with an adaptive framework such as covariate shift adaptation in tackling the nonstationarity in BCIs.

AB - Electroencephalogram (EEG) signals used in brain computer interfaces (BCIs) change over time, both within a single session and between sessions. Factors such as change in strategy by the user, sensorimotor learning, user fatigue, small differences in electrode position and muscular activity result in nonstationary EEG dynamics. Dealing with these characteristics when transferring from the calibration to a feedback session is a challenging but critical issue in BCI applications. To cope with this problem, a framework based on constant-Q filter bank Common Spatial Patterns (FBCSP) and Linear Discriminant Analysis (LDA) is proposed. This framework has been applied on dataset IVc from the BCI Competition III. Results show that the proposed method compares favorably with an adaptive framework such as covariate shift adaptation in tackling the nonstationarity in BCIs.

UR - http://www.icbme.ir/

UR - http://www.icbme.ir/

M3 - Conference contribution

VL - 2012

BT - Unknown Host Publication

ER -

Mohammadi R, Mahloojifar A, Coyle DH. Reducing nonstationary effects on motor imagery BCI using Constant-Q FBCSP. In Unknown Host Publication. Vol. 2012. 2012