Abstract
In this study, adaptive resonance theory (ART2) neural networks are investigated for on-line unsupervised recognition of EEG.spikes for epilepsy monitoring. ART2 networks are unsupervised self-organizing systems that cluster data into different classes. Learning is completed when these classes are labelled bv an expert and are saved in a look-up table for use by the system. Recognition of new data is accomplished by finding the class assigned by ART2 and searching through the table to get the proper labels. Unrecognized inputs are put into a new class for future labelling. In this study an ART2 neural network with 20 inputs was developed and trained using EEG data containing spike and non-spike waveforms. For comparison a 20 input multilayer perceptron was constructed and evaluated similarly. Evaluation with three sets of EEG patterns indicates that the ART2 network's performance is close to that of multilayer perceptron showing its high potential. Considering that ART2 can be trained with one or a few iterations (compared to thousands required for hackpropagation networks), monitoring systems with on-line training can be easily constructed. Such systems are highly desirable for long-term EEG monitoring due to large variations of spike waveforms that occur among individual patients and during long recording time periods.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the 1992 International Biomedical Engineering Days, IBED 1992 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 192-197 |
Number of pages | 6 |
ISBN (Electronic) | 0780307437, 9780780307438 |
DOIs | |
State | Published - Jan 1 1992 |
Externally published | Yes |
Event | 1992 International Biomedical Engineering Days, IBED 1992 - Istanbul, Turkey Duration: Aug 18 1992 → Aug 20 1992 |
Publication series
Name | Proceedings of the 1992 International Biomedical Engineering Days, IBED 1992 |
---|
Conference
Conference | 1992 International Biomedical Engineering Days, IBED 1992 |
---|---|
Country | Turkey |
City | Istanbul |
Period | 8/18/92 → 8/20/92 |
Fingerprint
ASJC Scopus subject areas
- Biomedical Engineering
Cite this
Detection of transient EEG patterns with adaptive unsupervised neural networks. / Özdamar, Özcan; Lopez, Carlos N.; Yaylali, Ilker.
Proceedings of the 1992 International Biomedical Engineering Days, IBED 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 192-197 247111 (Proceedings of the 1992 International Biomedical Engineering Days, IBED 1992).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Detection of transient EEG patterns with adaptive unsupervised neural networks
AU - Özdamar, Özcan
AU - Lopez, Carlos N.
AU - Yaylali, Ilker
PY - 1992/1/1
Y1 - 1992/1/1
N2 - In this study, adaptive resonance theory (ART2) neural networks are investigated for on-line unsupervised recognition of EEG.spikes for epilepsy monitoring. ART2 networks are unsupervised self-organizing systems that cluster data into different classes. Learning is completed when these classes are labelled bv an expert and are saved in a look-up table for use by the system. Recognition of new data is accomplished by finding the class assigned by ART2 and searching through the table to get the proper labels. Unrecognized inputs are put into a new class for future labelling. In this study an ART2 neural network with 20 inputs was developed and trained using EEG data containing spike and non-spike waveforms. For comparison a 20 input multilayer perceptron was constructed and evaluated similarly. Evaluation with three sets of EEG patterns indicates that the ART2 network's performance is close to that of multilayer perceptron showing its high potential. Considering that ART2 can be trained with one or a few iterations (compared to thousands required for hackpropagation networks), monitoring systems with on-line training can be easily constructed. Such systems are highly desirable for long-term EEG monitoring due to large variations of spike waveforms that occur among individual patients and during long recording time periods.
AB - In this study, adaptive resonance theory (ART2) neural networks are investigated for on-line unsupervised recognition of EEG.spikes for epilepsy monitoring. ART2 networks are unsupervised self-organizing systems that cluster data into different classes. Learning is completed when these classes are labelled bv an expert and are saved in a look-up table for use by the system. Recognition of new data is accomplished by finding the class assigned by ART2 and searching through the table to get the proper labels. Unrecognized inputs are put into a new class for future labelling. In this study an ART2 neural network with 20 inputs was developed and trained using EEG data containing spike and non-spike waveforms. For comparison a 20 input multilayer perceptron was constructed and evaluated similarly. Evaluation with three sets of EEG patterns indicates that the ART2 network's performance is close to that of multilayer perceptron showing its high potential. Considering that ART2 can be trained with one or a few iterations (compared to thousands required for hackpropagation networks), monitoring systems with on-line training can be easily constructed. Such systems are highly desirable for long-term EEG monitoring due to large variations of spike waveforms that occur among individual patients and during long recording time periods.
UR - http://www.scopus.com/inward/record.url?scp=0003126669&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0003126669&partnerID=8YFLogxK
U2 - 10.1109/IBED.1992.247111
DO - 10.1109/IBED.1992.247111
M3 - Conference contribution
AN - SCOPUS:0003126669
T3 - Proceedings of the 1992 International Biomedical Engineering Days, IBED 1992
SP - 192
EP - 197
BT - Proceedings of the 1992 International Biomedical Engineering Days, IBED 1992
PB - Institute of Electrical and Electronics Engineers Inc.
ER -