Neural network design considerations for EEG spike detection

Russell C. Eberhart, Roy W. Dobbins, William Webber

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

Abstract

Neural networks are being used to analyze electroencephalogram (EEG) signals for the detection of epileptiform spikes. A review is presented of the design considerations involved in implementing a real-time spike detection system. Issues addressed are generally in two areas. The first is the characterization of the source data. For example, decisions must be made relative to data rates, the number of data channels, and whether to use raw data, or preprocessed data in the form of spike parameters. The second is the selection of the neural network architecture and the specific implementation of that architecture. For example, choices must be made between supervised and unsupervised learning schemes, and among the many available network learning algorithms. A discussion is presented of interim results in an EEG spike detection project, the goal of which is to provide real-time spike detection capability for a multibed epilepsy monitoring unit.

Original languageEnglish (US)
Title of host publicationBioengineering, Proceedings of the Northeast Conference
EditorsSoren Buus
PublisherPubl by IEEE
Pages97-98
Number of pages2
StatePublished - Dec 1 1989
EventProceedings of the Fifteenth Annual Northeast Bioengineering Conference - Boston, MA, USA
Duration: Mar 27 1989Mar 28 1989

Other

OtherProceedings of the Fifteenth Annual Northeast Bioengineering Conference
CityBoston, MA, USA
Period3/27/893/28/89

Fingerprint

Electroencephalography
Neural networks
Unsupervised learning
Supervised learning
Network architecture
Learning algorithms
Monitoring

ASJC Scopus subject areas

  • Chemical Engineering(all)

Cite this

Eberhart, R. C., Dobbins, R. W., & Webber, W. (1989). Neural network design considerations for EEG spike detection. In S. Buus (Ed.), Bioengineering, Proceedings of the Northeast Conference (pp. 97-98). Publ by IEEE.

Neural network design considerations for EEG spike detection. / Eberhart, Russell C.; Dobbins, Roy W.; Webber, William.

Bioengineering, Proceedings of the Northeast Conference. ed. / Soren Buus. Publ by IEEE, 1989. p. 97-98.

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

Eberhart, RC, Dobbins, RW & Webber, W 1989, Neural network design considerations for EEG spike detection. in S Buus (ed.), Bioengineering, Proceedings of the Northeast Conference. Publ by IEEE, pp. 97-98, Proceedings of the Fifteenth Annual Northeast Bioengineering Conference, Boston, MA, USA, 3/27/89.
Eberhart RC, Dobbins RW, Webber W. Neural network design considerations for EEG spike detection. In Buus S, editor, Bioengineering, Proceedings of the Northeast Conference. Publ by IEEE. 1989. p. 97-98
Eberhart, Russell C. ; Dobbins, Roy W. ; Webber, William. / Neural network design considerations for EEG spike detection. Bioengineering, Proceedings of the Northeast Conference. editor / Soren Buus. Publ by IEEE, 1989. pp. 97-98
@inproceedings{80a390e2a9654a739478f6434d96ca31,
title = "Neural network design considerations for EEG spike detection",
abstract = "Neural networks are being used to analyze electroencephalogram (EEG) signals for the detection of epileptiform spikes. A review is presented of the design considerations involved in implementing a real-time spike detection system. Issues addressed are generally in two areas. The first is the characterization of the source data. For example, decisions must be made relative to data rates, the number of data channels, and whether to use raw data, or preprocessed data in the form of spike parameters. The second is the selection of the neural network architecture and the specific implementation of that architecture. For example, choices must be made between supervised and unsupervised learning schemes, and among the many available network learning algorithms. A discussion is presented of interim results in an EEG spike detection project, the goal of which is to provide real-time spike detection capability for a multibed epilepsy monitoring unit.",
author = "Eberhart, {Russell C.} and Dobbins, {Roy W.} and William Webber",
year = "1989",
month = "12",
day = "1",
language = "English (US)",
pages = "97--98",
editor = "Soren Buus",
booktitle = "Bioengineering, Proceedings of the Northeast Conference",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Neural network design considerations for EEG spike detection

AU - Eberhart, Russell C.

AU - Dobbins, Roy W.

AU - Webber, William

PY - 1989/12/1

Y1 - 1989/12/1

N2 - Neural networks are being used to analyze electroencephalogram (EEG) signals for the detection of epileptiform spikes. A review is presented of the design considerations involved in implementing a real-time spike detection system. Issues addressed are generally in two areas. The first is the characterization of the source data. For example, decisions must be made relative to data rates, the number of data channels, and whether to use raw data, or preprocessed data in the form of spike parameters. The second is the selection of the neural network architecture and the specific implementation of that architecture. For example, choices must be made between supervised and unsupervised learning schemes, and among the many available network learning algorithms. A discussion is presented of interim results in an EEG spike detection project, the goal of which is to provide real-time spike detection capability for a multibed epilepsy monitoring unit.

AB - Neural networks are being used to analyze electroencephalogram (EEG) signals for the detection of epileptiform spikes. A review is presented of the design considerations involved in implementing a real-time spike detection system. Issues addressed are generally in two areas. The first is the characterization of the source data. For example, decisions must be made relative to data rates, the number of data channels, and whether to use raw data, or preprocessed data in the form of spike parameters. The second is the selection of the neural network architecture and the specific implementation of that architecture. For example, choices must be made between supervised and unsupervised learning schemes, and among the many available network learning algorithms. A discussion is presented of interim results in an EEG spike detection project, the goal of which is to provide real-time spike detection capability for a multibed epilepsy monitoring unit.

UR - http://www.scopus.com/inward/record.url?scp=0024876996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024876996&partnerID=8YFLogxK

M3 - Conference contribution

SP - 97

EP - 98

BT - Bioengineering, Proceedings of the Northeast Conference

A2 - Buus, Soren

PB - Publ by IEEE

ER -