Subject and class specific frequency bands selection for multiclass motor imagery classification

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

EEG-based discrimination among motor imagery states has been widely studied for brain-computer interfaces (BCIs) due to the great potential for real-life applications. However, in terms of designing a motor imagery-based BCI system, a lot of research in the literature either uses a frequency band of interest selected manually based on the visual analysis of EEG data or is set to a general broad band, causing performance degradation in classification. In this article, we propose a novel method of selecting subject and class specific frequency bands based on the analysis of a channel-frequency matrix, which we call a channel-frequency map. We operate the classification process for each frequency band individually, i.e., spatial filtering, feature extraction, and classification, and determine a class label for an input EEG by considering the outputs from multiple classifiers together at the end. From our experiments on a public dataset of BCI Competition IV (2008) II-a that includes four motor imagery tasks from nine subjects, the proposed algorithm outperformed the common spatial pattern (CSP) algorithm in a broad band and a filter bank CSP algorithm on average in terms of cross-validation and session-to-session transfer rate. Furthermore, a considerable increase of classification accuracy has been achieved for certain subjects. We also would like to note that the proposed data-driven frequency bands selection method is applicable to other kinds of single-trial EEG classifications that are based on modulations of brain rhythms, by no means limited to motor imagery-based BCI applications.

Original languageEnglish
Pages (from-to)123-130
Number of pages8
JournalInternational Journal of Imaging Systems and Technology
Volume21
Issue number2
DOIs
Publication statusPublished - 2011 Jun 1

Fingerprint

Brain computer interface
Frequency bands
Electroencephalography
Filter banks
Feature extraction
Labels
Brain
Classifiers
Modulation
Degradation
Experiments

Keywords

  • brain-computer interface
  • electroencephalography
  • ERD/ERS
  • frequency bands selection
  • motor imagery classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Computer Vision and Pattern Recognition
  • Software

Cite this

@article{cbaeea4044944bc5a368cdaa3f6b9f02,
title = "Subject and class specific frequency bands selection for multiclass motor imagery classification",
abstract = "EEG-based discrimination among motor imagery states has been widely studied for brain-computer interfaces (BCIs) due to the great potential for real-life applications. However, in terms of designing a motor imagery-based BCI system, a lot of research in the literature either uses a frequency band of interest selected manually based on the visual analysis of EEG data or is set to a general broad band, causing performance degradation in classification. In this article, we propose a novel method of selecting subject and class specific frequency bands based on the analysis of a channel-frequency matrix, which we call a channel-frequency map. We operate the classification process for each frequency band individually, i.e., spatial filtering, feature extraction, and classification, and determine a class label for an input EEG by considering the outputs from multiple classifiers together at the end. From our experiments on a public dataset of BCI Competition IV (2008) II-a that includes four motor imagery tasks from nine subjects, the proposed algorithm outperformed the common spatial pattern (CSP) algorithm in a broad band and a filter bank CSP algorithm on average in terms of cross-validation and session-to-session transfer rate. Furthermore, a considerable increase of classification accuracy has been achieved for certain subjects. We also would like to note that the proposed data-driven frequency bands selection method is applicable to other kinds of single-trial EEG classifications that are based on modulations of brain rhythms, by no means limited to motor imagery-based BCI applications.",
keywords = "brain-computer interface, electroencephalography, ERD/ERS, frequency bands selection, motor imagery classification",
author = "Heung-Il Suk and Lee, {Seong Whan}",
year = "2011",
month = "6",
day = "1",
doi = "10.1002/ima.20283",
language = "English",
volume = "21",
pages = "123--130",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "2",

}

TY - JOUR

T1 - Subject and class specific frequency bands selection for multiclass motor imagery classification

AU - Suk, Heung-Il

AU - Lee, Seong Whan

PY - 2011/6/1

Y1 - 2011/6/1

N2 - EEG-based discrimination among motor imagery states has been widely studied for brain-computer interfaces (BCIs) due to the great potential for real-life applications. However, in terms of designing a motor imagery-based BCI system, a lot of research in the literature either uses a frequency band of interest selected manually based on the visual analysis of EEG data or is set to a general broad band, causing performance degradation in classification. In this article, we propose a novel method of selecting subject and class specific frequency bands based on the analysis of a channel-frequency matrix, which we call a channel-frequency map. We operate the classification process for each frequency band individually, i.e., spatial filtering, feature extraction, and classification, and determine a class label for an input EEG by considering the outputs from multiple classifiers together at the end. From our experiments on a public dataset of BCI Competition IV (2008) II-a that includes four motor imagery tasks from nine subjects, the proposed algorithm outperformed the common spatial pattern (CSP) algorithm in a broad band and a filter bank CSP algorithm on average in terms of cross-validation and session-to-session transfer rate. Furthermore, a considerable increase of classification accuracy has been achieved for certain subjects. We also would like to note that the proposed data-driven frequency bands selection method is applicable to other kinds of single-trial EEG classifications that are based on modulations of brain rhythms, by no means limited to motor imagery-based BCI applications.

AB - EEG-based discrimination among motor imagery states has been widely studied for brain-computer interfaces (BCIs) due to the great potential for real-life applications. However, in terms of designing a motor imagery-based BCI system, a lot of research in the literature either uses a frequency band of interest selected manually based on the visual analysis of EEG data or is set to a general broad band, causing performance degradation in classification. In this article, we propose a novel method of selecting subject and class specific frequency bands based on the analysis of a channel-frequency matrix, which we call a channel-frequency map. We operate the classification process for each frequency band individually, i.e., spatial filtering, feature extraction, and classification, and determine a class label for an input EEG by considering the outputs from multiple classifiers together at the end. From our experiments on a public dataset of BCI Competition IV (2008) II-a that includes four motor imagery tasks from nine subjects, the proposed algorithm outperformed the common spatial pattern (CSP) algorithm in a broad band and a filter bank CSP algorithm on average in terms of cross-validation and session-to-session transfer rate. Furthermore, a considerable increase of classification accuracy has been achieved for certain subjects. We also would like to note that the proposed data-driven frequency bands selection method is applicable to other kinds of single-trial EEG classifications that are based on modulations of brain rhythms, by no means limited to motor imagery-based BCI applications.

KW - brain-computer interface

KW - electroencephalography

KW - ERD/ERS

KW - frequency bands selection

KW - motor imagery classification

UR - http://www.scopus.com/inward/record.url?scp=79955883498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955883498&partnerID=8YFLogxK

U2 - 10.1002/ima.20283

DO - 10.1002/ima.20283

M3 - Article

AN - SCOPUS:79955883498

VL - 21

SP - 123

EP - 130

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 2

ER -