Detection of the EEG K-complex wave with neural networks

Isaac N. Bankman, Vincent G. Sigillito, Robert A Wise, Philip L Smith

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

Abstract

The K-complex detection task is approached by first extracting morphological features that quantify the visual recognition criteria used for both acceptance and rejection of candidate waveforms. The features are based on amplitude and duration measurements. These features are used as the inputs of multivariate discrimination methods. The performance of Fisher's linear discriminant with multilayer feedforward neural networks (MLFNs) in discriminating the K-complex and background EEG is compared. The results show that the use of the MLFN on feature information can provide a reliable K-complex detection with significantly better performance than that of the linear discriminant. This difference in performance can be seen on the receiver operating characteristics curves that show the true positive against the false positives.

Original languageEnglish (US)
Title of host publicationProc 4 Annu Symp Comput Based Med Syst
PublisherPubl by IEEE
Pages280-287
Number of pages8
ISBN (Print)0818621648
StatePublished - 1991
EventProceedings of the 4th Annual Symposium on Computer-Based Medical Systems -
Duration: May 12 1991May 14 1991

Other

OtherProceedings of the 4th Annual Symposium on Computer-Based Medical Systems
Period5/12/915/14/91

Fingerprint

Feedforward neural networks
Multilayer neural networks
Electroencephalography
Neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Bankman, I. N., Sigillito, V. G., Wise, R. A., & Smith, P. L. (1991). Detection of the EEG K-complex wave with neural networks. In Proc 4 Annu Symp Comput Based Med Syst (pp. 280-287). Publ by IEEE.

Detection of the EEG K-complex wave with neural networks. / Bankman, Isaac N.; Sigillito, Vincent G.; Wise, Robert A; Smith, Philip L.

Proc 4 Annu Symp Comput Based Med Syst. Publ by IEEE, 1991. p. 280-287.

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

Bankman, IN, Sigillito, VG, Wise, RA & Smith, PL 1991, Detection of the EEG K-complex wave with neural networks. in Proc 4 Annu Symp Comput Based Med Syst. Publ by IEEE, pp. 280-287, Proceedings of the 4th Annual Symposium on Computer-Based Medical Systems, 5/12/91.
Bankman IN, Sigillito VG, Wise RA, Smith PL. Detection of the EEG K-complex wave with neural networks. In Proc 4 Annu Symp Comput Based Med Syst. Publ by IEEE. 1991. p. 280-287
Bankman, Isaac N. ; Sigillito, Vincent G. ; Wise, Robert A ; Smith, Philip L. / Detection of the EEG K-complex wave with neural networks. Proc 4 Annu Symp Comput Based Med Syst. Publ by IEEE, 1991. pp. 280-287
@inproceedings{c3fa7c239dd04569b992f89cfe3a8a8e,
title = "Detection of the EEG K-complex wave with neural networks",
abstract = "The K-complex detection task is approached by first extracting morphological features that quantify the visual recognition criteria used for both acceptance and rejection of candidate waveforms. The features are based on amplitude and duration measurements. These features are used as the inputs of multivariate discrimination methods. The performance of Fisher's linear discriminant with multilayer feedforward neural networks (MLFNs) in discriminating the K-complex and background EEG is compared. The results show that the use of the MLFN on feature information can provide a reliable K-complex detection with significantly better performance than that of the linear discriminant. This difference in performance can be seen on the receiver operating characteristics curves that show the true positive against the false positives.",
author = "Bankman, {Isaac N.} and Sigillito, {Vincent G.} and Wise, {Robert A} and Smith, {Philip L}",
year = "1991",
language = "English (US)",
isbn = "0818621648",
pages = "280--287",
booktitle = "Proc 4 Annu Symp Comput Based Med Syst",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Detection of the EEG K-complex wave with neural networks

AU - Bankman, Isaac N.

AU - Sigillito, Vincent G.

AU - Wise, Robert A

AU - Smith, Philip L

PY - 1991

Y1 - 1991

N2 - The K-complex detection task is approached by first extracting morphological features that quantify the visual recognition criteria used for both acceptance and rejection of candidate waveforms. The features are based on amplitude and duration measurements. These features are used as the inputs of multivariate discrimination methods. The performance of Fisher's linear discriminant with multilayer feedforward neural networks (MLFNs) in discriminating the K-complex and background EEG is compared. The results show that the use of the MLFN on feature information can provide a reliable K-complex detection with significantly better performance than that of the linear discriminant. This difference in performance can be seen on the receiver operating characteristics curves that show the true positive against the false positives.

AB - The K-complex detection task is approached by first extracting morphological features that quantify the visual recognition criteria used for both acceptance and rejection of candidate waveforms. The features are based on amplitude and duration measurements. These features are used as the inputs of multivariate discrimination methods. The performance of Fisher's linear discriminant with multilayer feedforward neural networks (MLFNs) in discriminating the K-complex and background EEG is compared. The results show that the use of the MLFN on feature information can provide a reliable K-complex detection with significantly better performance than that of the linear discriminant. This difference in performance can be seen on the receiver operating characteristics curves that show the true positive against the false positives.

UR - http://www.scopus.com/inward/record.url?scp=0025846060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025846060&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818621648

SP - 280

EP - 287

BT - Proc 4 Annu Symp Comput Based Med Syst

PB - Publ by IEEE

ER -