Finding predictive EEG complexity features for classification of epileptic and psychogenic nonepileptic seizures using imperialist competitive algorithm

N. Ahmadi, Evelien Carrette, A.P. Aldenkamp, M. Pechenizkiy

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)
92 Downloads (Pure)

Abstract

In this study, the imperialist competitive algorithm (ICA) is applied for classification of epileptic seizure and psychogenic nonepileptic seizure (PNES). For this purpose, after decomposing the EEG signal into five sub-bands and extracting some complexity features of EEG, the ICA is applied to find the predictive feature subset that maximizes the classification performance in the frequency spectrum. Results show that the spectral entropy and Renyi entropy are the most important EEG features as they are always appeared in the best feature subsets when applying different classifiers. Also, it is observed that the SVM-RBF and SVM-linear models are the best classifiers resulting in highest performance metrics compared to other classifiers. Our study shows that the reported algorithm is able to classify the epileptic seizure and PNES with a very high classification metrics.

Original languageEnglish
Title of host publicationProceedings - 31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages164-169
Number of pages6
ISBN (Electronic)978-1-5386-6060-7
DOIs
Publication statusPublished - 20 Jul 2018
Event31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018 - Karlstad, Sweden
Duration: 18 Jun 201821 Jun 2018

Conference

Conference31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018
CountrySweden
CityKarlstad
Period18/06/1821/06/18

Keywords

  • complexity
  • EEG
  • epileptic seizures
  • imperialist competitive algorithm
  • PNES

Fingerprint Dive into the research topics of 'Finding predictive EEG complexity features for classification of epileptic and psychogenic nonepileptic seizures using imperialist competitive algorithm'. Together they form a unique fingerprint.

Cite this