An artificial neural-network approach to erp classification

Lalit Gupta, Dennis L. Molfese, Ravi Tammana

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Artificial neural network-based approaches were developed to classify event-related potential (ERP) waveforms. The networks utilized scalp-recorded ERP returns from six electrode sites. These ERPs were evoked as one individual responded to a series of auditorily presented object names while viewing various objects on a computer screen. The ERPs at the electrode sites were classified as a match decision or a no-match decision. A three-layer backpropagation neural network model was selected to formulate a global and a local classification approach. The backpropagation network in the global approach was designed to operate on a single ERP response which was the average of the ERP responses generated at the six electrode sites. The local ERP classification system consisted of six three-layer backpropagation networks. Each network was designed to operate on the ERPs generated at a single electrode site. A small data base consisting of eight match and eight no-match ERP responses was used to train and test the networks in a variety of ways. The results obtained clearly show that the neural network-based classifiers are able to discriminate with a high degree of accuracy between match and no-match conditions in ERP waveforms.

Original languageEnglish (US)
Pages (from-to)311-330
Number of pages20
JournalBrain and Cognition
Volume27
Issue number3
DOIs
StatePublished - Apr 1995

Fingerprint

Evoked Potentials
Electrodes
Neural Networks (Computer)
Artificial Neural Network
Event-related Potentials
Scalp
Names
Databases

ASJC Scopus subject areas

  • Neuropsychology and Physiological Psychology
  • Experimental and Cognitive Psychology
  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Cite this

An artificial neural-network approach to erp classification. / Gupta, Lalit; Molfese, Dennis L.; Tammana, Ravi.

In: Brain and Cognition, Vol. 27, No. 3, 04.1995, p. 311-330.

Research output: Contribution to journalArticle

Gupta, Lalit ; Molfese, Dennis L. ; Tammana, Ravi. / An artificial neural-network approach to erp classification. In: Brain and Cognition. 1995 ; Vol. 27, No. 3. pp. 311-330.
@article{cd96fde615f146a884ed9d11f410061f,
title = "An artificial neural-network approach to erp classification",
abstract = "Artificial neural network-based approaches were developed to classify event-related potential (ERP) waveforms. The networks utilized scalp-recorded ERP returns from six electrode sites. These ERPs were evoked as one individual responded to a series of auditorily presented object names while viewing various objects on a computer screen. The ERPs at the electrode sites were classified as a match decision or a no-match decision. A three-layer backpropagation neural network model was selected to formulate a global and a local classification approach. The backpropagation network in the global approach was designed to operate on a single ERP response which was the average of the ERP responses generated at the six electrode sites. The local ERP classification system consisted of six three-layer backpropagation networks. Each network was designed to operate on the ERPs generated at a single electrode site. A small data base consisting of eight match and eight no-match ERP responses was used to train and test the networks in a variety of ways. The results obtained clearly show that the neural network-based classifiers are able to discriminate with a high degree of accuracy between match and no-match conditions in ERP waveforms.",
author = "Lalit Gupta and Molfese, {Dennis L.} and Ravi Tammana",
year = "1995",
month = "4",
doi = "10.1006/brcg.1995.1025",
language = "English (US)",
volume = "27",
pages = "311--330",
journal = "Brain and Cognition",
issn = "0278-2626",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - An artificial neural-network approach to erp classification

AU - Gupta, Lalit

AU - Molfese, Dennis L.

AU - Tammana, Ravi

PY - 1995/4

Y1 - 1995/4

N2 - Artificial neural network-based approaches were developed to classify event-related potential (ERP) waveforms. The networks utilized scalp-recorded ERP returns from six electrode sites. These ERPs were evoked as one individual responded to a series of auditorily presented object names while viewing various objects on a computer screen. The ERPs at the electrode sites were classified as a match decision or a no-match decision. A three-layer backpropagation neural network model was selected to formulate a global and a local classification approach. The backpropagation network in the global approach was designed to operate on a single ERP response which was the average of the ERP responses generated at the six electrode sites. The local ERP classification system consisted of six three-layer backpropagation networks. Each network was designed to operate on the ERPs generated at a single electrode site. A small data base consisting of eight match and eight no-match ERP responses was used to train and test the networks in a variety of ways. The results obtained clearly show that the neural network-based classifiers are able to discriminate with a high degree of accuracy between match and no-match conditions in ERP waveforms.

AB - Artificial neural network-based approaches were developed to classify event-related potential (ERP) waveforms. The networks utilized scalp-recorded ERP returns from six electrode sites. These ERPs were evoked as one individual responded to a series of auditorily presented object names while viewing various objects on a computer screen. The ERPs at the electrode sites were classified as a match decision or a no-match decision. A three-layer backpropagation neural network model was selected to formulate a global and a local classification approach. The backpropagation network in the global approach was designed to operate on a single ERP response which was the average of the ERP responses generated at the six electrode sites. The local ERP classification system consisted of six three-layer backpropagation networks. Each network was designed to operate on the ERPs generated at a single electrode site. A small data base consisting of eight match and eight no-match ERP responses was used to train and test the networks in a variety of ways. The results obtained clearly show that the neural network-based classifiers are able to discriminate with a high degree of accuracy between match and no-match conditions in ERP waveforms.

UR - http://www.scopus.com/inward/record.url?scp=0029278640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029278640&partnerID=8YFLogxK

U2 - 10.1006/brcg.1995.1025

DO - 10.1006/brcg.1995.1025

M3 - Article

C2 - 7626279

AN - SCOPUS:0029278640

VL - 27

SP - 311

EP - 330

JO - Brain and Cognition

JF - Brain and Cognition

SN - 0278-2626

IS - 3

ER -