Multilevel neural network system for EEG spike detection

Ozcan Ozdamar, Ilker Yaylali, Prasanna Jayaker, Carlos N. Lopez

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

30 Citations (Scopus)

Abstract

The design and evaluation of an artificial neural network system for the detection of epileptogenic spikes is described. The system is composed of smaller neural network modules which are trained individually and organized in two levels. The first-level modules are trained to recognize candidate spikes in single referential electroencephalogram (EEG) channels. Original digitized data with a running window of 100 ms provided the input for the first-level modules. A second-level module is used for the spatial integration of 16 first-level modules. The system was trained and tested using clinical EEG data interpreted by four expert electroencephalographers. The results show that spikes can be recognized directly from unprocessed EEG and a second-level neural network can integrate spatial EEG information and eliminate false detections.

Original languageEnglish
Title of host publicationUnknown Host Publication Title
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages272-279
Number of pages8
ISBN (Print)0818621648
StatePublished - Jan 1 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

Electroencephalography
Neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ozdamar, O., Yaylali, I., Jayaker, P., & Lopez, C. N. (1991). Multilevel neural network system for EEG spike detection. In Unknown Host Publication Title (pp. 272-279). Piscataway, NJ, United States: Publ by IEEE.

Multilevel neural network system for EEG spike detection. / Ozdamar, Ozcan; Yaylali, Ilker; Jayaker, Prasanna; Lopez, Carlos N.

Unknown Host Publication Title. Piscataway, NJ, United States : Publ by IEEE, 1991. p. 272-279.

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

Ozdamar, O, Yaylali, I, Jayaker, P & Lopez, CN 1991, Multilevel neural network system for EEG spike detection. in Unknown Host Publication Title. Publ by IEEE, Piscataway, NJ, United States, pp. 272-279, Proceedings of the 4th Annual Symposium on Computer-Based Medical Systems, 5/12/91.
Ozdamar O, Yaylali I, Jayaker P, Lopez CN. Multilevel neural network system for EEG spike detection. In Unknown Host Publication Title. Piscataway, NJ, United States: Publ by IEEE. 1991. p. 272-279
Ozdamar, Ozcan ; Yaylali, Ilker ; Jayaker, Prasanna ; Lopez, Carlos N. / Multilevel neural network system for EEG spike detection. Unknown Host Publication Title. Piscataway, NJ, United States : Publ by IEEE, 1991. pp. 272-279
@inproceedings{9f352c87c93643c9ac9b1330f8e14581,
title = "Multilevel neural network system for EEG spike detection",
abstract = "The design and evaluation of an artificial neural network system for the detection of epileptogenic spikes is described. The system is composed of smaller neural network modules which are trained individually and organized in two levels. The first-level modules are trained to recognize candidate spikes in single referential electroencephalogram (EEG) channels. Original digitized data with a running window of 100 ms provided the input for the first-level modules. A second-level module is used for the spatial integration of 16 first-level modules. The system was trained and tested using clinical EEG data interpreted by four expert electroencephalographers. The results show that spikes can be recognized directly from unprocessed EEG and a second-level neural network can integrate spatial EEG information and eliminate false detections.",
author = "Ozcan Ozdamar and Ilker Yaylali and Prasanna Jayaker and Lopez, {Carlos N.}",
year = "1991",
month = "1",
day = "1",
language = "English",
isbn = "0818621648",
pages = "272--279",
booktitle = "Unknown Host Publication Title",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Multilevel neural network system for EEG spike detection

AU - Ozdamar, Ozcan

AU - Yaylali, Ilker

AU - Jayaker, Prasanna

AU - Lopez, Carlos N.

PY - 1991/1/1

Y1 - 1991/1/1

N2 - The design and evaluation of an artificial neural network system for the detection of epileptogenic spikes is described. The system is composed of smaller neural network modules which are trained individually and organized in two levels. The first-level modules are trained to recognize candidate spikes in single referential electroencephalogram (EEG) channels. Original digitized data with a running window of 100 ms provided the input for the first-level modules. A second-level module is used for the spatial integration of 16 first-level modules. The system was trained and tested using clinical EEG data interpreted by four expert electroencephalographers. The results show that spikes can be recognized directly from unprocessed EEG and a second-level neural network can integrate spatial EEG information and eliminate false detections.

AB - The design and evaluation of an artificial neural network system for the detection of epileptogenic spikes is described. The system is composed of smaller neural network modules which are trained individually and organized in two levels. The first-level modules are trained to recognize candidate spikes in single referential electroencephalogram (EEG) channels. Original digitized data with a running window of 100 ms provided the input for the first-level modules. A second-level module is used for the spatial integration of 16 first-level modules. The system was trained and tested using clinical EEG data interpreted by four expert electroencephalographers. The results show that spikes can be recognized directly from unprocessed EEG and a second-level neural network can integrate spatial EEG information and eliminate false detections.

UR - http://www.scopus.com/inward/record.url?scp=0025849914&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025849914&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818621648

SP - 272

EP - 279

BT - Unknown Host Publication Title

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -