Artifact rejection for improving the performance of evoked potential neural network classifiers

Lalit Gupta, Dennis L. Molfese, Ravi Tammana, Mark McAvoy

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

Abstract

This paper is aimed at improving, through artifact rejection, the performance of neural network evoked potential (EP) classifiers designed to detect match/mismatch conditions. A cluster analysis approach is formulated to identify artifacts that occur in the signals used for training the neural network classifiers. The clustering based artifact detection algorithm uses a distance measure resulting from a nonlinear alignment procedure designed to optimally align EP signals. Match and mismatch EPs collected for network training are clustered and the identified artifact signals are excluded from the training set. Artifacts that occur during testing are also identified and rejected by including an additional output in the neural net classifier for the artifact class. Preliminary experiments conducted show significant improvements in classification accuracy when the proposed artifact rejection methods are incorporated in the training and testing phases of a neural network EP classifier.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Pages676-686
Number of pages11
Edition2
StatePublished - Dec 1 1995
EventOptical Engineering Midwest'95. Part 2 (of 2) - Chicago, IL, USA
Duration: May 18 1995May 19 1995

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Number2
Volume2622
ISSN (Print)0277-786X

Other

OtherOptical Engineering Midwest'95. Part 2 (of 2)
CityChicago, IL, USA
Period5/18/955/19/95

Fingerprint

Bioelectric potentials
classifiers
rejection
artifacts
Classifiers
Neural networks
education
Cluster analysis
Testing
neural nets
cluster analysis
alignment
Experiments
output

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Gupta, L., Molfese, D. L., Tammana, R., & McAvoy, M. (1995). Artifact rejection for improving the performance of evoked potential neural network classifiers. In Proceedings of SPIE - The International Society for Optical Engineering (2 ed., pp. 676-686). (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 2622, No. 2).

Artifact rejection for improving the performance of evoked potential neural network classifiers. / Gupta, Lalit; Molfese, Dennis L.; Tammana, Ravi; McAvoy, Mark.

Proceedings of SPIE - The International Society for Optical Engineering. 2. ed. 1995. p. 676-686 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 2622, No. 2).

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

Gupta, L, Molfese, DL, Tammana, R & McAvoy, M 1995, Artifact rejection for improving the performance of evoked potential neural network classifiers. in Proceedings of SPIE - The International Society for Optical Engineering. 2 edn, Proceedings of SPIE - The International Society for Optical Engineering, no. 2, vol. 2622, pp. 676-686, Optical Engineering Midwest'95. Part 2 (of 2), Chicago, IL, USA, 5/18/95.
Gupta L, Molfese DL, Tammana R, McAvoy M. Artifact rejection for improving the performance of evoked potential neural network classifiers. In Proceedings of SPIE - The International Society for Optical Engineering. 2 ed. 1995. p. 676-686. (Proceedings of SPIE - The International Society for Optical Engineering; 2).
Gupta, Lalit ; Molfese, Dennis L. ; Tammana, Ravi ; McAvoy, Mark. / Artifact rejection for improving the performance of evoked potential neural network classifiers. Proceedings of SPIE - The International Society for Optical Engineering. 2. ed. 1995. pp. 676-686 (Proceedings of SPIE - The International Society for Optical Engineering; 2).
@inproceedings{1ac3a97dad0e423c98e4f75b40257abb,
title = "Artifact rejection for improving the performance of evoked potential neural network classifiers",
abstract = "This paper is aimed at improving, through artifact rejection, the performance of neural network evoked potential (EP) classifiers designed to detect match/mismatch conditions. A cluster analysis approach is formulated to identify artifacts that occur in the signals used for training the neural network classifiers. The clustering based artifact detection algorithm uses a distance measure resulting from a nonlinear alignment procedure designed to optimally align EP signals. Match and mismatch EPs collected for network training are clustered and the identified artifact signals are excluded from the training set. Artifacts that occur during testing are also identified and rejected by including an additional output in the neural net classifier for the artifact class. Preliminary experiments conducted show significant improvements in classification accuracy when the proposed artifact rejection methods are incorporated in the training and testing phases of a neural network EP classifier.",
author = "Lalit Gupta and Molfese, {Dennis L.} and Ravi Tammana and Mark McAvoy",
year = "1995",
month = "12",
day = "1",
language = "English (US)",
isbn = "0819419869",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
number = "2",
pages = "676--686",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
edition = "2",

}

TY - GEN

T1 - Artifact rejection for improving the performance of evoked potential neural network classifiers

AU - Gupta, Lalit

AU - Molfese, Dennis L.

AU - Tammana, Ravi

AU - McAvoy, Mark

PY - 1995/12/1

Y1 - 1995/12/1

N2 - This paper is aimed at improving, through artifact rejection, the performance of neural network evoked potential (EP) classifiers designed to detect match/mismatch conditions. A cluster analysis approach is formulated to identify artifacts that occur in the signals used for training the neural network classifiers. The clustering based artifact detection algorithm uses a distance measure resulting from a nonlinear alignment procedure designed to optimally align EP signals. Match and mismatch EPs collected for network training are clustered and the identified artifact signals are excluded from the training set. Artifacts that occur during testing are also identified and rejected by including an additional output in the neural net classifier for the artifact class. Preliminary experiments conducted show significant improvements in classification accuracy when the proposed artifact rejection methods are incorporated in the training and testing phases of a neural network EP classifier.

AB - This paper is aimed at improving, through artifact rejection, the performance of neural network evoked potential (EP) classifiers designed to detect match/mismatch conditions. A cluster analysis approach is formulated to identify artifacts that occur in the signals used for training the neural network classifiers. The clustering based artifact detection algorithm uses a distance measure resulting from a nonlinear alignment procedure designed to optimally align EP signals. Match and mismatch EPs collected for network training are clustered and the identified artifact signals are excluded from the training set. Artifacts that occur during testing are also identified and rejected by including an additional output in the neural net classifier for the artifact class. Preliminary experiments conducted show significant improvements in classification accuracy when the proposed artifact rejection methods are incorporated in the training and testing phases of a neural network EP classifier.

UR - http://www.scopus.com/inward/record.url?scp=0029487549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029487549&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029487549

SN - 0819419869

SN - 9780819419866

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 676

EP - 686

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -