Spatio-temporal modeling for dense array ERP classification

Srinivas Kota, Lalit Gupta, Dennis L Molfese, Ravi Vaidyanathan

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

Abstract

A new strategy is introduced to exploit the enhanced spatial resolution offered by dense electrode arrays and to solve the dimensionality problem that plagues the design and evaluation of practical dense array event-related potential (ERP) classifiers. A spatiotemporal model is introduced to observe the dense array ERP amplitude variations across channels and time, simultaneously. Dimensionality reduction is achieved by selecting elements of the spatio-temporal arrays which differ in their probability distributions across the brain activity classes. Each selected spatio-temporal element is classified using an univariate Gaussian classifier and the resulting decisions are fused into a decision fusion vector which is classified using a discrete Bayes vector classifier. Using ERPs from a Stroop color test, it is shown that the performance improves significantly when the strategy is applied to normalized spatio-temporal ERP arrays. The main advantage of the new strategy is that it is not constrained by the dimensionality of the ERP vector. Consequently, it can be used to design ERP classifiers specialized for individual test subjects without having to collect a large number of ERPs from groups of subjects in order to solve the dimensionality problem.

Original languageEnglish (US)
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
Pages2091-2094
Number of pages4
StatePublished - Dec 1 2008
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada
Duration: Aug 20 2008Aug 25 2008

Publication series

NameProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"

Conference

Conference30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
CountryCanada
CityVancouver, BC
Period8/20/088/25/08

Fingerprint

Evoked Potentials
Classifiers
Enterprise resource planning
Stroop Test
Plague
Probability distributions
Brain
Fusion reactions
Color
Electrodes

Keywords

  • Decision fusion
  • Dense arrays
  • Dimensionality reduction
  • Event-related potentials
  • Spatio-temporal modeling

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Kota, S., Gupta, L., Molfese, D. L., & Vaidyanathan, R. (2008). Spatio-temporal modeling for dense array ERP classification. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 (pp. 2091-2094). [4649605] (Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology").

Spatio-temporal modeling for dense array ERP classification. / Kota, Srinivas; Gupta, Lalit; Molfese, Dennis L; Vaidyanathan, Ravi.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 2091-2094 4649605 (Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology").

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

Kota, S, Gupta, L, Molfese, DL & Vaidyanathan, R 2008, Spatio-temporal modeling for dense array ERP classification. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08., 4649605, Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 2091-2094, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08, Vancouver, BC, Canada, 8/20/08.
Kota S, Gupta L, Molfese DL, Vaidyanathan R. Spatio-temporal modeling for dense array ERP classification. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 2091-2094. 4649605. (Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology").
Kota, Srinivas ; Gupta, Lalit ; Molfese, Dennis L ; Vaidyanathan, Ravi. / Spatio-temporal modeling for dense array ERP classification. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. pp. 2091-2094 (Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology").
@inproceedings{24b674af315d4a96bff64a34aebbbe8e,
title = "Spatio-temporal modeling for dense array ERP classification",
abstract = "A new strategy is introduced to exploit the enhanced spatial resolution offered by dense electrode arrays and to solve the dimensionality problem that plagues the design and evaluation of practical dense array event-related potential (ERP) classifiers. A spatiotemporal model is introduced to observe the dense array ERP amplitude variations across channels and time, simultaneously. Dimensionality reduction is achieved by selecting elements of the spatio-temporal arrays which differ in their probability distributions across the brain activity classes. Each selected spatio-temporal element is classified using an univariate Gaussian classifier and the resulting decisions are fused into a decision fusion vector which is classified using a discrete Bayes vector classifier. Using ERPs from a Stroop color test, it is shown that the performance improves significantly when the strategy is applied to normalized spatio-temporal ERP arrays. The main advantage of the new strategy is that it is not constrained by the dimensionality of the ERP vector. Consequently, it can be used to design ERP classifiers specialized for individual test subjects without having to collect a large number of ERPs from groups of subjects in order to solve the dimensionality problem.",
keywords = "Decision fusion, Dense arrays, Dimensionality reduction, Event-related potentials, Spatio-temporal modeling",
author = "Srinivas Kota and Lalit Gupta and Molfese, {Dennis L} and Ravi Vaidyanathan",
year = "2008",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781424418152",
series = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - {"}Personalized Healthcare through Technology{"}",
pages = "2091--2094",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08",

}

TY - GEN

T1 - Spatio-temporal modeling for dense array ERP classification

AU - Kota, Srinivas

AU - Gupta, Lalit

AU - Molfese, Dennis L

AU - Vaidyanathan, Ravi

PY - 2008/12/1

Y1 - 2008/12/1

N2 - A new strategy is introduced to exploit the enhanced spatial resolution offered by dense electrode arrays and to solve the dimensionality problem that plagues the design and evaluation of practical dense array event-related potential (ERP) classifiers. A spatiotemporal model is introduced to observe the dense array ERP amplitude variations across channels and time, simultaneously. Dimensionality reduction is achieved by selecting elements of the spatio-temporal arrays which differ in their probability distributions across the brain activity classes. Each selected spatio-temporal element is classified using an univariate Gaussian classifier and the resulting decisions are fused into a decision fusion vector which is classified using a discrete Bayes vector classifier. Using ERPs from a Stroop color test, it is shown that the performance improves significantly when the strategy is applied to normalized spatio-temporal ERP arrays. The main advantage of the new strategy is that it is not constrained by the dimensionality of the ERP vector. Consequently, it can be used to design ERP classifiers specialized for individual test subjects without having to collect a large number of ERPs from groups of subjects in order to solve the dimensionality problem.

AB - A new strategy is introduced to exploit the enhanced spatial resolution offered by dense electrode arrays and to solve the dimensionality problem that plagues the design and evaluation of practical dense array event-related potential (ERP) classifiers. A spatiotemporal model is introduced to observe the dense array ERP amplitude variations across channels and time, simultaneously. Dimensionality reduction is achieved by selecting elements of the spatio-temporal arrays which differ in their probability distributions across the brain activity classes. Each selected spatio-temporal element is classified using an univariate Gaussian classifier and the resulting decisions are fused into a decision fusion vector which is classified using a discrete Bayes vector classifier. Using ERPs from a Stroop color test, it is shown that the performance improves significantly when the strategy is applied to normalized spatio-temporal ERP arrays. The main advantage of the new strategy is that it is not constrained by the dimensionality of the ERP vector. Consequently, it can be used to design ERP classifiers specialized for individual test subjects without having to collect a large number of ERPs from groups of subjects in order to solve the dimensionality problem.

KW - Decision fusion

KW - Dense arrays

KW - Dimensionality reduction

KW - Event-related potentials

KW - Spatio-temporal modeling

UR - http://www.scopus.com/inward/record.url?scp=61849161262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61849161262&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424418152

T3 - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"

SP - 2091

EP - 2094

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08

ER -