Developing a logistic regression model with cross-correlation for motor imagery signal recognition

Siuly, Yan Li, Jinglong Wu, Jingjing Yang

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

16 Citations (Scopus)

Abstract

Classification of motor imagery (MI)-based electroencephalogram (EEG) signals is a key issue for the development of brain-computer interface (BCI) systems. The objective of this study is to develop an algorithm that can distinguish two categories of MI EEG signals. In this paper, we propose a new classification algorithm for two-class MI signals recognition in BCIs. The proposed scheme develops a novel cross-correlation-based feature extractor, which is aided with a logistic regression model. The present method is tested on dataset IVa of BCI Competition III, which contain two-class MI data for five subjects. The performance is objectively computed using a k-fold cross validation (k=10) method on the testing set for each subject. The results of this study are compared with the recently reported eight methods in the literature. The results demonstrate that our proposed method outperforms the eight methods in terms of the average classification accuracy.

Original languageEnglish
Title of host publication2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011
Pages502-507
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 5th IEEE/ICME International Conference on Complex Medical Engineering, CME 2011 - Harbin, China
Duration: May 22 2011May 25 2011

Other

Other2011 5th IEEE/ICME International Conference on Complex Medical Engineering, CME 2011
CountryChina
CityHarbin
Period5/22/115/25/11

Fingerprint

Logistics
Brain computer interface
Electroencephalography
Testing

Keywords

  • Brain-computer interface (BCI)
  • Cross-correlation technique
  • Electroencephalogram (EEG)
  • Logistic regression model
  • Motor imagery (MI)

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Siuly, Li, Y., Wu, J., & Yang, J. (2011). Developing a logistic regression model with cross-correlation for motor imagery signal recognition. In 2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011 (pp. 502-507). [5876793] https://doi.org/10.1109/ICCME.2011.5876793

Developing a logistic regression model with cross-correlation for motor imagery signal recognition. / Siuly; Li, Yan; Wu, Jinglong; Yang, Jingjing.

2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011. 2011. p. 502-507 5876793.

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

Siuly, Li, Y, Wu, J & Yang, J 2011, Developing a logistic regression model with cross-correlation for motor imagery signal recognition. in 2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011., 5876793, pp. 502-507, 2011 5th IEEE/ICME International Conference on Complex Medical Engineering, CME 2011, Harbin, China, 5/22/11. https://doi.org/10.1109/ICCME.2011.5876793
Siuly, Li Y, Wu J, Yang J. Developing a logistic regression model with cross-correlation for motor imagery signal recognition. In 2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011. 2011. p. 502-507. 5876793 https://doi.org/10.1109/ICCME.2011.5876793
Siuly ; Li, Yan ; Wu, Jinglong ; Yang, Jingjing. / Developing a logistic regression model with cross-correlation for motor imagery signal recognition. 2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011. 2011. pp. 502-507
@inproceedings{6154458f382f4481bddc7142cbfb45fa,
title = "Developing a logistic regression model with cross-correlation for motor imagery signal recognition",
abstract = "Classification of motor imagery (MI)-based electroencephalogram (EEG) signals is a key issue for the development of brain-computer interface (BCI) systems. The objective of this study is to develop an algorithm that can distinguish two categories of MI EEG signals. In this paper, we propose a new classification algorithm for two-class MI signals recognition in BCIs. The proposed scheme develops a novel cross-correlation-based feature extractor, which is aided with a logistic regression model. The present method is tested on dataset IVa of BCI Competition III, which contain two-class MI data for five subjects. The performance is objectively computed using a k-fold cross validation (k=10) method on the testing set for each subject. The results of this study are compared with the recently reported eight methods in the literature. The results demonstrate that our proposed method outperforms the eight methods in terms of the average classification accuracy.",
keywords = "Brain-computer interface (BCI), Cross-correlation technique, Electroencephalogram (EEG), Logistic regression model, Motor imagery (MI)",
author = "Siuly and Yan Li and Jinglong Wu and Jingjing Yang",
year = "2011",
doi = "10.1109/ICCME.2011.5876793",
language = "English",
isbn = "9781424493241",
pages = "502--507",
booktitle = "2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011",

}

TY - GEN

T1 - Developing a logistic regression model with cross-correlation for motor imagery signal recognition

AU - Siuly,

AU - Li, Yan

AU - Wu, Jinglong

AU - Yang, Jingjing

PY - 2011

Y1 - 2011

N2 - Classification of motor imagery (MI)-based electroencephalogram (EEG) signals is a key issue for the development of brain-computer interface (BCI) systems. The objective of this study is to develop an algorithm that can distinguish two categories of MI EEG signals. In this paper, we propose a new classification algorithm for two-class MI signals recognition in BCIs. The proposed scheme develops a novel cross-correlation-based feature extractor, which is aided with a logistic regression model. The present method is tested on dataset IVa of BCI Competition III, which contain two-class MI data for five subjects. The performance is objectively computed using a k-fold cross validation (k=10) method on the testing set for each subject. The results of this study are compared with the recently reported eight methods in the literature. The results demonstrate that our proposed method outperforms the eight methods in terms of the average classification accuracy.

AB - Classification of motor imagery (MI)-based electroencephalogram (EEG) signals is a key issue for the development of brain-computer interface (BCI) systems. The objective of this study is to develop an algorithm that can distinguish two categories of MI EEG signals. In this paper, we propose a new classification algorithm for two-class MI signals recognition in BCIs. The proposed scheme develops a novel cross-correlation-based feature extractor, which is aided with a logistic regression model. The present method is tested on dataset IVa of BCI Competition III, which contain two-class MI data for five subjects. The performance is objectively computed using a k-fold cross validation (k=10) method on the testing set for each subject. The results of this study are compared with the recently reported eight methods in the literature. The results demonstrate that our proposed method outperforms the eight methods in terms of the average classification accuracy.

KW - Brain-computer interface (BCI)

KW - Cross-correlation technique

KW - Electroencephalogram (EEG)

KW - Logistic regression model

KW - Motor imagery (MI)

UR - http://www.scopus.com/inward/record.url?scp=79959947624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959947624&partnerID=8YFLogxK

U2 - 10.1109/ICCME.2011.5876793

DO - 10.1109/ICCME.2011.5876793

M3 - Conference contribution

AN - SCOPUS:79959947624

SN - 9781424493241

SP - 502

EP - 507

BT - 2011 IEEE/ICME International Conference on Complex Medical Engineering, CME 2011

ER -