Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks

Yonghong Huang, Deniz Erdogmus, Santosh Mathan, Misha Pavel

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

6 Citations (Scopus)

Abstract

In this paper, we describe a system for detecting encephalography (EEG) signatures of visual recognition events evoked in a single trial during rapid serial visual presentation (RSVP). In order to investigate the viability of nonlinear approaches in EEG detection and assess the performance comparison, we applied three classifiers (linear logistic regression model, Laplacian classifier, and spectral maximum mutual information projection) in the detection tasks. The EEG was recorded using 32 electrodes during the rapid image presentation (50ms/100ms per image). Subjects were instructed to push a button when they recognize a target image. The results suggest that while the detection of single trial EEG-based recognition is possible, taking advantage of the nonlinear techniques requires data representation that would overcome the non-stationarity of the EEG signals.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages1136-1142
Number of pages7
StatePublished - 2006
EventInternational Joint Conference on Neural Networks 2006, IJCNN '06 - Vancouver, BC, Canada
Duration: Jul 16 2006Jul 21 2006

Other

OtherInternational Joint Conference on Neural Networks 2006, IJCNN '06
CountryCanada
CityVancouver, BC
Period7/16/067/21/06

Fingerprint

Enterprise resource planning
Classifiers
Logistics
Electrodes

ASJC Scopus subject areas

  • Software

Cite this

Huang, Y., Erdogmus, D., Mathan, S., & Pavel, M. (2006). Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks. In IEEE International Conference on Neural Networks - Conference Proceedings (pp. 1136-1142). [1716229]

Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks. / Huang, Yonghong; Erdogmus, Deniz; Mathan, Santosh; Pavel, Misha.

IEEE International Conference on Neural Networks - Conference Proceedings. 2006. p. 1136-1142 1716229.

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

Huang, Y, Erdogmus, D, Mathan, S & Pavel, M 2006, Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks. in IEEE International Conference on Neural Networks - Conference Proceedings., 1716229, pp. 1136-1142, International Joint Conference on Neural Networks 2006, IJCNN '06, Vancouver, BC, Canada, 7/16/06.
Huang Y, Erdogmus D, Mathan S, Pavel M. Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks. In IEEE International Conference on Neural Networks - Conference Proceedings. 2006. p. 1136-1142. 1716229
Huang, Yonghong ; Erdogmus, Deniz ; Mathan, Santosh ; Pavel, Misha. / Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks. IEEE International Conference on Neural Networks - Conference Proceedings. 2006. pp. 1136-1142
@inproceedings{043c79bc6c9f4f459528be2a43818bf9,
title = "Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks",
abstract = "In this paper, we describe a system for detecting encephalography (EEG) signatures of visual recognition events evoked in a single trial during rapid serial visual presentation (RSVP). In order to investigate the viability of nonlinear approaches in EEG detection and assess the performance comparison, we applied three classifiers (linear logistic regression model, Laplacian classifier, and spectral maximum mutual information projection) in the detection tasks. The EEG was recorded using 32 electrodes during the rapid image presentation (50ms/100ms per image). Subjects were instructed to push a button when they recognize a target image. The results suggest that while the detection of single trial EEG-based recognition is possible, taking advantage of the nonlinear techniques requires data representation that would overcome the non-stationarity of the EEG signals.",
author = "Yonghong Huang and Deniz Erdogmus and Santosh Mathan and Misha Pavel",
year = "2006",
language = "English (US)",
isbn = "0780394909",
pages = "1136--1142",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - Comparison of linear and nonlinear approaches on single trial ERP detection in rapid serial visual presentation tasks

AU - Huang, Yonghong

AU - Erdogmus, Deniz

AU - Mathan, Santosh

AU - Pavel, Misha

PY - 2006

Y1 - 2006

N2 - In this paper, we describe a system for detecting encephalography (EEG) signatures of visual recognition events evoked in a single trial during rapid serial visual presentation (RSVP). In order to investigate the viability of nonlinear approaches in EEG detection and assess the performance comparison, we applied three classifiers (linear logistic regression model, Laplacian classifier, and spectral maximum mutual information projection) in the detection tasks. The EEG was recorded using 32 electrodes during the rapid image presentation (50ms/100ms per image). Subjects were instructed to push a button when they recognize a target image. The results suggest that while the detection of single trial EEG-based recognition is possible, taking advantage of the nonlinear techniques requires data representation that would overcome the non-stationarity of the EEG signals.

AB - In this paper, we describe a system for detecting encephalography (EEG) signatures of visual recognition events evoked in a single trial during rapid serial visual presentation (RSVP). In order to investigate the viability of nonlinear approaches in EEG detection and assess the performance comparison, we applied three classifiers (linear logistic regression model, Laplacian classifier, and spectral maximum mutual information projection) in the detection tasks. The EEG was recorded using 32 electrodes during the rapid image presentation (50ms/100ms per image). Subjects were instructed to push a button when they recognize a target image. The results suggest that while the detection of single trial EEG-based recognition is possible, taking advantage of the nonlinear techniques requires data representation that would overcome the non-stationarity of the EEG signals.

UR - http://www.scopus.com/inward/record.url?scp=40649085358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40649085358&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780394909

SN - 9780780394902

SP - 1136

EP - 1142

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -