A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection.

Tian Lan; Deniz Erdogmus; Lois Black; Jan Van Santen

A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection.

Tian Lan
, Deniz Erdogmus
, Lois Black
, Jan Van Santen

Research output: Contribution to journal › Article › peer-review

Abstract

Dimensionality reduction and feature selection is an important aspect of electroencephalography based event related potential detection systems such as brain computer interfaces. In our study, a predefined sequence of letters was presented to subjects in a Rapid Serial Visual Presentation (RSVP) paradigm. EEG data were collected and analyzed offline. A linear discriminant analysis (LDA) classifier was designed as the ERP (Event Related Potential) detector for its simplicity. Different dimensionality reduction and feature selection methods were applied and compared in a greedy wrapper framework. Experimental results showed that PCA with the first 10 principal components for each channel performed best and could be used in both online and offline systems.

Original language	English (US)
Pages (from-to)	6329-6332
Number of pages	4
Journal	Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
State	Published - 2010
Externally published	Yes

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Signal Processing
Biomedical Engineering
Health Informatics

Cite this

A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection. / Lan, Tian; Erdogmus, Deniz; Black, Lois et al.
In: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 2010, p. 6329-6332.

Research output: Contribution to journal › Article › peer-review

@article{7135c5c5597c41bda4494c6ac3faf682,

title = "A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection.",

abstract = "Dimensionality reduction and feature selection is an important aspect of electroencephalography based event related potential detection systems such as brain computer interfaces. In our study, a predefined sequence of letters was presented to subjects in a Rapid Serial Visual Presentation (RSVP) paradigm. EEG data were collected and analyzed offline. A linear discriminant analysis (LDA) classifier was designed as the ERP (Event Related Potential) detector for its simplicity. Different dimensionality reduction and feature selection methods were applied and compared in a greedy wrapper framework. Experimental results showed that PCA with the first 10 principal components for each channel performed best and could be used in both online and offline systems.",

author = "Tian Lan and Deniz Erdogmus and Lois Black and \{Van Santen\}, Jan",

year = "2010",

language = "English (US)",

pages = "6329--6332",

journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",

issn = "1557-170X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection.

AU - Lan, Tian

AU - Erdogmus, Deniz

AU - Black, Lois

AU - Van Santen, Jan

PY - 2010

Y1 - 2010

N2 - Dimensionality reduction and feature selection is an important aspect of electroencephalography based event related potential detection systems such as brain computer interfaces. In our study, a predefined sequence of letters was presented to subjects in a Rapid Serial Visual Presentation (RSVP) paradigm. EEG data were collected and analyzed offline. A linear discriminant analysis (LDA) classifier was designed as the ERP (Event Related Potential) detector for its simplicity. Different dimensionality reduction and feature selection methods were applied and compared in a greedy wrapper framework. Experimental results showed that PCA with the first 10 principal components for each channel performed best and could be used in both online and offline systems.

AB - Dimensionality reduction and feature selection is an important aspect of electroencephalography based event related potential detection systems such as brain computer interfaces. In our study, a predefined sequence of letters was presented to subjects in a Rapid Serial Visual Presentation (RSVP) paradigm. EEG data were collected and analyzed offline. A linear discriminant analysis (LDA) classifier was designed as the ERP (Event Related Potential) detector for its simplicity. Different dimensionality reduction and feature selection methods were applied and compared in a greedy wrapper framework. Experimental results showed that PCA with the first 10 principal components for each channel performed best and could be used in both online and offline systems.

UR - https://www.scopus.com/pages/publications/84903859876

UR - http://www.scopus.com/inward/citedby.url?scp=84903859876&partnerID=8YFLogxK

M3 - Article

C2 - 21097171

SN - 1557-170X

SP - 6329

EP - 6332

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

ER -

A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection.

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this