Multichannel fusion models for the parametric classification of differential brain activity

Lalit Gupta, Beomsu Chung, Mandyam D. Srinath, Dennis L Molfese, Hyunseok Kook

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

This paper introduces parametric multichannel fusion models to exploit the different but complementary brain activity information recorded from multiple channels in order to accurately classify differential brain activity into their respective categories. A parametric weighted decision fusion model and two parametric weighted data fusion models are introduced for the classification of averaged multichannel evoked potentials (EPs). The decision fusion model combines the independent decisions of each channel classifier into a decision fusion vector and a parametric classifier is designed to determine the EP class from the discrete decision fusion vector. The data fusion models include the weighted EP-sum model in which the fusion vector is a linear combination of the multichannel EPs and the EP-concatenation model in which the fusion vector is a vector-concatenation of the multichannel EPs. The discrete Karhunen-Loeve transform (DKLT) is used to select features for each channel classifier and from each data fusion vector. The difficulty in estimating the probability density function (PDF) parameters from a small number of averaged EPs is identified and the class conditional PDFs of the feature vectors of averaged EPs are, therefore, derived in terms of the PDFs of the single-trial EPs. Multivariate parametric classifiers are developed for each fusion strategy and the performances of the different strategies are compared by classifying 14-channel EPs collected from five subjects involved in making explicit match/mismatch comparisons between sequentially presented stimuli. It is shown that the performance improves by incorporating weights in the fusion rules and that the best performance is obtained using multichannel EP concatenation. It is also noted that the fusion strategies introduced are also applicable to other problems involving the classification of multicategory multivariate signals generated from multiple sources.

Original languageEnglish (US)
Pages (from-to)1869-1881
Number of pages13
JournalIEEE Transactions on Biomedical Engineering
Volume52
Issue number11
DOIs
StatePublished - Nov 1 2005

Fingerprint

Bioelectric potentials
Brain
Data fusion
Classifiers
Probability density function

Keywords

  • Evoked potentials
  • Multisensor fusion
  • Parametric classification

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Multichannel fusion models for the parametric classification of differential brain activity. / Gupta, Lalit; Chung, Beomsu; Srinath, Mandyam D.; Molfese, Dennis L; Kook, Hyunseok.

In: IEEE Transactions on Biomedical Engineering, Vol. 52, No. 11, 01.11.2005, p. 1869-1881.

Research output: Contribution to journalArticle

Gupta, Lalit ; Chung, Beomsu ; Srinath, Mandyam D. ; Molfese, Dennis L ; Kook, Hyunseok. / Multichannel fusion models for the parametric classification of differential brain activity. In: IEEE Transactions on Biomedical Engineering. 2005 ; Vol. 52, No. 11. pp. 1869-1881.
@article{f89a0cd8bc1d472cbf10d087ee13eb2d,
title = "Multichannel fusion models for the parametric classification of differential brain activity",
abstract = "This paper introduces parametric multichannel fusion models to exploit the different but complementary brain activity information recorded from multiple channels in order to accurately classify differential brain activity into their respective categories. A parametric weighted decision fusion model and two parametric weighted data fusion models are introduced for the classification of averaged multichannel evoked potentials (EPs). The decision fusion model combines the independent decisions of each channel classifier into a decision fusion vector and a parametric classifier is designed to determine the EP class from the discrete decision fusion vector. The data fusion models include the weighted EP-sum model in which the fusion vector is a linear combination of the multichannel EPs and the EP-concatenation model in which the fusion vector is a vector-concatenation of the multichannel EPs. The discrete Karhunen-Loeve transform (DKLT) is used to select features for each channel classifier and from each data fusion vector. The difficulty in estimating the probability density function (PDF) parameters from a small number of averaged EPs is identified and the class conditional PDFs of the feature vectors of averaged EPs are, therefore, derived in terms of the PDFs of the single-trial EPs. Multivariate parametric classifiers are developed for each fusion strategy and the performances of the different strategies are compared by classifying 14-channel EPs collected from five subjects involved in making explicit match/mismatch comparisons between sequentially presented stimuli. It is shown that the performance improves by incorporating weights in the fusion rules and that the best performance is obtained using multichannel EP concatenation. It is also noted that the fusion strategies introduced are also applicable to other problems involving the classification of multicategory multivariate signals generated from multiple sources.",
keywords = "Evoked potentials, Multisensor fusion, Parametric classification",
author = "Lalit Gupta and Beomsu Chung and Srinath, {Mandyam D.} and Molfese, {Dennis L} and Hyunseok Kook",
year = "2005",
month = "11",
day = "1",
doi = "10.1109/TBME.2005.856272",
language = "English (US)",
volume = "52",
pages = "1869--1881",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "11",

}

TY - JOUR

T1 - Multichannel fusion models for the parametric classification of differential brain activity

AU - Gupta, Lalit

AU - Chung, Beomsu

AU - Srinath, Mandyam D.

AU - Molfese, Dennis L

AU - Kook, Hyunseok

PY - 2005/11/1

Y1 - 2005/11/1

N2 - This paper introduces parametric multichannel fusion models to exploit the different but complementary brain activity information recorded from multiple channels in order to accurately classify differential brain activity into their respective categories. A parametric weighted decision fusion model and two parametric weighted data fusion models are introduced for the classification of averaged multichannel evoked potentials (EPs). The decision fusion model combines the independent decisions of each channel classifier into a decision fusion vector and a parametric classifier is designed to determine the EP class from the discrete decision fusion vector. The data fusion models include the weighted EP-sum model in which the fusion vector is a linear combination of the multichannel EPs and the EP-concatenation model in which the fusion vector is a vector-concatenation of the multichannel EPs. The discrete Karhunen-Loeve transform (DKLT) is used to select features for each channel classifier and from each data fusion vector. The difficulty in estimating the probability density function (PDF) parameters from a small number of averaged EPs is identified and the class conditional PDFs of the feature vectors of averaged EPs are, therefore, derived in terms of the PDFs of the single-trial EPs. Multivariate parametric classifiers are developed for each fusion strategy and the performances of the different strategies are compared by classifying 14-channel EPs collected from five subjects involved in making explicit match/mismatch comparisons between sequentially presented stimuli. It is shown that the performance improves by incorporating weights in the fusion rules and that the best performance is obtained using multichannel EP concatenation. It is also noted that the fusion strategies introduced are also applicable to other problems involving the classification of multicategory multivariate signals generated from multiple sources.

AB - This paper introduces parametric multichannel fusion models to exploit the different but complementary brain activity information recorded from multiple channels in order to accurately classify differential brain activity into their respective categories. A parametric weighted decision fusion model and two parametric weighted data fusion models are introduced for the classification of averaged multichannel evoked potentials (EPs). The decision fusion model combines the independent decisions of each channel classifier into a decision fusion vector and a parametric classifier is designed to determine the EP class from the discrete decision fusion vector. The data fusion models include the weighted EP-sum model in which the fusion vector is a linear combination of the multichannel EPs and the EP-concatenation model in which the fusion vector is a vector-concatenation of the multichannel EPs. The discrete Karhunen-Loeve transform (DKLT) is used to select features for each channel classifier and from each data fusion vector. The difficulty in estimating the probability density function (PDF) parameters from a small number of averaged EPs is identified and the class conditional PDFs of the feature vectors of averaged EPs are, therefore, derived in terms of the PDFs of the single-trial EPs. Multivariate parametric classifiers are developed for each fusion strategy and the performances of the different strategies are compared by classifying 14-channel EPs collected from five subjects involved in making explicit match/mismatch comparisons between sequentially presented stimuli. It is shown that the performance improves by incorporating weights in the fusion rules and that the best performance is obtained using multichannel EP concatenation. It is also noted that the fusion strategies introduced are also applicable to other problems involving the classification of multicategory multivariate signals generated from multiple sources.

KW - Evoked potentials

KW - Multisensor fusion

KW - Parametric classification

UR - http://www.scopus.com/inward/record.url?scp=27644599839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27644599839&partnerID=8YFLogxK

U2 - 10.1109/TBME.2005.856272

DO - 10.1109/TBME.2005.856272

M3 - Article

VL - 52

SP - 1869

EP - 1881

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 11

ER -