The Impact of Feature Selection on Epilepsy Diagnosis from EEG Signals: A Comparison of Dynamic Time Warping and Itakura-Saito Distance

Epileptic seizure detection is crucial for accurate diagnosis and effective treatment of epilepsy. Automated systems based on electroencephalogram signals play an important role in reducing the time, effort, and subjectivity involved in manual analysis performed by neurologists. However, many previo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Advances in Electrical and Computer Engineering Jg. 25; H. 3; S. 45 - 58
Hauptverfasser: EKIM, G., IKIZLER, N.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Stefan cel Mare University of Suceava 01.08.2025
Schlagworte:
ISSN:1582-7445, 1844-7600
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Epileptic seizure detection is crucial for accurate diagnosis and effective treatment of epilepsy. Automated systems based on electroencephalogram signals play an important role in reducing the time, effort, and subjectivity involved in manual analysis performed by neurologists. However, many previous studies mainly focused on timedomain similarity measures, fuzzy logic models, or neural network-based classifiers and did not fully explore the potential of spectral similarity features for seizure detection. This study introduces a new approach by applying the Dynamic Time Warping method directly to power spectral density data obtained using the Welch method. This enables a spectral similarity analysis that is independent of time shifts and better reflects the non-stationary nature of brain signals. In addition, the Itakura-Saito distance is investigated for the first time for epileptic seizure detection and compared with the Dynamic Time Warping method. A twelve-feature vector was created using reference-based similarity measurements combined with energy and spectral features, and multiple classification methods were evaluated. Experimental results on the Bonn electroencephalogram dataset demonstrate that Dynamic Time Warping achieved the highest classification performance, with the Random Forest algorithm reaching 100% accuracy in binary tasks. These findings highlight the importance of spectral similarity features in improving automatic seizure detection systems and demonstrate the clinical value of the proposed approach. Index Terms--biomedical signal processing, decision support systems, epilepsy, feature extraction, machine learning.
AbstractList Epileptic seizure detection is crucial for accurate diagnosis and effective treatment of epilepsy. Automated systems based on electroencephalogram signals play an important role in reducing the time, effort, and subjectivity involved in manual analysis performed by neurologists. However, many previous studies mainly focused on timedomain similarity measures, fuzzy logic models, or neural network-based classifiers and did not fully explore the potential of spectral similarity features for seizure detection. This study introduces a new approach by applying the Dynamic Time Warping method directly to power spectral density data obtained using the Welch method. This enables a spectral similarity analysis that is independent of time shifts and better reflects the non-stationary nature of brain signals. In addition, the Itakura-Saito distance is investigated for the first time for epileptic seizure detection and compared with the Dynamic Time Warping method. A twelve-feature vector was created using reference-based similarity measurements combined with energy and spectral features, and multiple classification methods were evaluated. Experimental results on the Bonn electroencephalogram dataset demonstrate that Dynamic Time Warping achieved the highest classification performance, with the Random Forest algorithm reaching 100% accuracy in binary tasks. These findings highlight the importance of spectral similarity features in improving automatic seizure detection systems and demonstrate the clinical value of the proposed approach. Index Terms--biomedical signal processing, decision support systems, epilepsy, feature extraction, machine learning.
Epileptic seizure detection is crucial for accurate diagnosis and effective treatment of epilepsy. Automated systems based on electroencephalogram signals play an important role in reducing the time, effort, and subjectivity involved in manual analysis performed by neurologists. However, many previous studies mainly focused on timedomain similarity measures, fuzzy logic models, or neural network-based classifiers and did not fully explore the potential of spectral similarity features for seizure detection. This study introduces a new approach by applying the Dynamic Time Warping method directly to power spectral density data obtained using the Welch method. This enables a spectral similarity analysis that is independent of time shifts and better reflects the non-stationary nature of brain signals. In addition, the Itakura-Saito distance is investigated for the first time for epileptic seizure detection and compared with the Dynamic Time Warping method. A twelve-feature vector was created using reference-based similarity measurements combined with energy and spectral features, and multiple classification methods were evaluated. Experimental results on the Bonn electroencephalogram dataset demonstrate that Dynamic Time Warping achieved the highest classification performance, with the Random Forest algorithm reaching 100% accuracy in binary tasks. These findings highlight the importance of spectral similarity features in improving automatic seizure detection systems and demonstrate the clinical value of the proposed approach.
Epileptic seizure detection is crucial for accurate diagnosis and effective treatment of epilepsy. Automated systems based on electroencephalogram signals play an important role in reducing the time, effort, and subjectivity involved in manual analysis performed by neurologists. However, many previous studies mainly focused on time-domain similarity measures, fuzzy logic models, or neural network-based classifiers and did not fully explore the potential of spectral similarity features for seizure detection. This study introduces a new approach by applying the Dynamic Time Warping method directly to power spectral density data obtained using the Welch method. This enables a spectral similarity analysis that is independent of time shifts and better reflects the non-stationary nature of brain signals. In addition, the Itakura-Saito distance is investigated for the first time for epileptic seizure detection and compared with the Dynamic Time Warping method. A twelve-feature vector was created using reference-based similarity measurements combined with energy and spectral features, and multiple classification methods were evaluated. Experimental results on the Bonn electroencephalogram dataset demonstrate that Dynamic Time Warping achieved the highest classification performance, with the Random Forest algorithm reaching 100% accuracy in binary tasks. These findings highlight the importance of spectral similarity features in improving automatic seizure detection systems and demonstrate the clinical value of the proposed approach.
Audience Academic
Author EKIM, G.
IKIZLER, N.
Author_xml – sequence: 1
  givenname: G.
  surname: EKIM
  fullname: EKIM, G.
– sequence: 2
  givenname: N.
  surname: IKIZLER
  fullname: IKIZLER, N.
BookMark eNptkUFr3DAQhU1IIWmac66Cnr2RJVm2e1s2TroQ6GG39ChG8shRu5aM5Bz2F-RvV5sthUKZgRHivY9h3sfi0gePRXFX0ZXglbxf95t-xSirV5RTKi-K66oVomwkpZf5XbesbISor4rblJymQjSsZVxeF2_7FyTbaQazkGDJI8LyGpHs8IBmccGT3P3sDjinI3lwMPqQXCI2hon0_RPZudHDIX0ha7IJGRNdOpkseTh6mJwhezch-QFxdn4k4AeyXeDXa4RyB24JGZkW8AY_FR9s5uDtn3lTfH_s95uv5fO3p-1m_Vwa1kpZQteKVugK9TCYuhWGGTDWiIpqUWvDEJpOYi0HybqGW9kabXWHUGteNcCB3xTbM3cI8FPN0U0QjyqAU-8fIY4K4uLMAZXNeEBqKOu4YLbpdA3Ydah5LgM6sz6fWSNkufM2LBHM5JJR61aKqmKyEVm1-o8q14D5PjlGm6_7r-H-bDAxpBTR_l2zouqUtjqlrU5pq_e0-W-HlZ6Y
Cites_doi 10.1007/s10470-021-01805-2
10.1109/JSEN.2020.3026032
10.1016/j.jksuci.2018.04.014
10.1016/j.bspc.2021.103031
10.59277/ROMJIST.2024.1.08
10.1016/j.bspc.2019.101707
10.1016/j.eswa.2021.115175
10.20895/infotel.v15i1.874
10.1080/03091902.2017.1394388
10.4316/AECE.2017.04001
10.1002/ima.22565
10.1016/j.amjmed.2021.01.038
10.59277/ROMJIST.2023.3-4.10
10.1007/s00170-023-11280-w
10.2339/politeknik.672077
10.2339/politeknik.1605362
10.1016/j.eswa.2016.09.037
10.1016/j.jocs.2023.101943
10.1016/j.procs.2019.05.007
10.52876/jcs.1226579
10.1038/s41598-021-83337-3
10.1103/PhysRevE.64.061907
10.1016/j.compbiomed.2017.01.017
10.1007/s11045-018-0628-7
10.1080/01616412.2018.1508544
10.1016/j.engappai.2020.103975
10.1007/s11062-012-9268-y
10.1016/j.neuroimage.2009.06.057
10.1093/brain/awae385
10.1016/j.neurol.2023.12.005
10.1016/j.jestch.2025.102005
10.2339/politeknik.1055549
10.1186/s40708-018-0084-z
10.3233/THC-171343
10.1080/03772063.2021.1913074
10.1109/TITB.2009.2017939
10.1016/j.artmed.2017.12.004
ContentType Journal Article
Copyright COPYRIGHT 2025 Stefan cel Mare University of Suceava
Copyright_xml – notice: COPYRIGHT 2025 Stefan cel Mare University of Suceava
DBID AAYXX
CITATION
DOA
DOI 10.4316/AECE.2025.03006
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1844-7600
EndPage 58
ExternalDocumentID oai_doaj_org_article_f84cae0c029342f79b5ae99eb3b3bcab
A864112674
10_4316_AECE_2025_03006
GeographicLocations Turkey
GeographicLocations_xml – name: Turkey
GroupedDBID 23M
5GY
5VS
AAKPC
AAYXX
ABJCF
ADBBV
AENEX
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BAIFH
BBTPI
BCNDV
BENPR
BGLVJ
C1A
CCPQU
CITATION
E3Z
GROUPED_DOAJ
HCIFZ
IAO
IGS
IPNFZ
ITC
KQ8
M7S
OK1
PHGZM
PHGZT
PQGLB
PTHSS
PV9
RIG
RZL
TR2
ADMLS
ID FETCH-LOGICAL-c2866-a98484b1ebddc584c2cacfc410b45bc2ea796e56d62973f68cbfb9ea5b317a3a3
IEDL.DBID DOA
ISSN 1582-7445
IngestDate Mon Nov 03 22:01:33 EST 2025
Wed Dec 10 10:35:35 EST 2025
Tue Dec 02 03:52:10 EST 2025
Wed Nov 05 20:55:00 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2866-a98484b1ebddc584c2cacfc410b45bc2ea796e56d62973f68cbfb9ea5b317a3a3
OpenAccessLink https://doaj.org/article/f84cae0c029342f79b5ae99eb3b3bcab
PageCount 14
ParticipantIDs doaj_primary_oai_doaj_org_article_f84cae0c029342f79b5ae99eb3b3bcab
gale_infotracmisc_A864112674
gale_infotracacademiconefile_A864112674
crossref_primary_10_4316_AECE_2025_03006
PublicationCentury 2000
PublicationDate 20250801
PublicationDateYYYYMMDD 2025-08-01
PublicationDate_xml – month: 08
  year: 2025
  text: 20250801
  day: 01
PublicationDecade 2020
PublicationTitle Advances in Electrical and Computer Engineering
PublicationYear 2025
Publisher Stefan cel Mare University of Suceava
Publisher_xml – name: Stefan cel Mare University of Suceava
References Tzallas (10.1109/TITB.2009.2017939) 2009; 13
Sharmila (10.1080/03091902.2017.1394388) 2017; 41
Radman (10.1109/JSEN.2020.3026032) 2021; 21
Sulaiman (10.1109/UKSIM.2011.23) 2011
Ahmed (10.1016/j.compbiomed.2017.01.017) 2017; 82
Choubey (10.1007/s11045-018-0628-7) 2019; 30
Ikizler (10.1016/j.jestch.2025.102005) 2025; 64
Amin (10.1016/j.bspc.2019.101707) 2020; 56
TUNCER (10.2339/politeknik.672077) 2022; 25
Jana (10.1080/03772063.2021.1913074) 2023; 69
Harpale (10.1016/j.jksuci.2018.04.014) 2021; 33
Liu (10.3233/THC-171343) 2017; 25
Mandhouj (10.1007/s10470-021-01805-2) 2021; 108
Varli (10.1016/j.jocs.2023.101943) 2023; 67
CANYURT (10.52876/jcs.1226579) 2023; 8
Zhang (10.1016/j.engappai.2020.103975) 2020; 96
Tuncer (10.1016/j.eswa.2021.115175) 2021; 182
Andrzejak (10.1103/PhysRevE.64.061907) 2001; 64
Ashokkumar (10.1002/ima.22565) 2021; 31
NING (10.59277/ROMJIST.2024.1.08) 2024; 2024
Thomas (10.1109/ICASSP.2016.7471775) 2016
de Toffol (10.1016/j.neurol.2023.12.005) 2024; 180
Ahmad (10.1109/ICPR.2014.583) 2014
BORLEA (10.4316/AECE.2017.04001) 2017; 17
Paul (10.1186/s40708-018-0084-z) 2018; 5
Ikizler (10.2339/politeknik.1605362) 2025; 28
Kinaci (10.2339/politeknik.1055549) 2024; 27
Vysata (10.1007/s11062-012-9268-y) 2012; 44
Pyrzowski (10.1038/s41598-021-83337-3) 2021; 11
MIHALACHE (10.59277/ROMJIST.2023.3-4.10) 2023; 2023
Hosseini (10.1016/j.artmed.2017.12.004) 2018; 84
Ahuja (10.1016/j.procs.2019.05.007) 2019; 152
Aarabi (10.1016/j.neuroimage.2009.06.057) 2009; 48
Tchane Djogdom (10.1007/s00170-023-11280-w) 2023; 126
Zhang (10.1109/BMEI.2008.254) 2008
Trevelyan (10.1093/brain/awae385) 2025; 148
Milligan (10.1016/j.amjmed.2021.01.038) 2021; 134
Saini (10.1080/01616412.2018.1508544) 2018; 40
Eltrass (10.1016/j.bspc.2021.103031) 2021; 70
Melinda (10.20895/infotel.v15i1.874) 2023; 15
Alotaiby (10.1109/ICEDSA.2016.7818505) 2016
Amorim (10.1016/j.eswa.2016.09.037) 2017; 67
References_xml – volume: 108
  start-page: 101
  year: 2021
  ident: 10.1007/s10470-021-01805-2
  publication-title: Analog Integrated Circuits and Signal Processing
  doi: 10.1007/s10470-021-01805-2
– volume: 21
  start-page: 3533
  year: 2021
  ident: 10.1109/JSEN.2020.3026032
  publication-title: IEEE Sensors Journal
  doi: 10.1109/JSEN.2020.3026032
– volume: 33
  start-page: 668
  year: 2021
  ident: 10.1016/j.jksuci.2018.04.014
  publication-title: Journal of King Saud University - Computer and Information Sciences
  doi: 10.1016/j.jksuci.2018.04.014
– volume: 70
  start-page: 103031
  year: 2021
  ident: 10.1016/j.bspc.2021.103031
  publication-title: Biomedical Signal Processing and Control
  doi: 10.1016/j.bspc.2021.103031
– start-page: 69
  year: 2011
  ident: 10.1109/UKSIM.2011.23
– volume: 2024
  start-page: 106
  year: 2024
  ident: 10.59277/ROMJIST.2024.1.08
  publication-title: Romanian Journal of Information Science and Technology
  doi: 10.59277/ROMJIST.2024.1.08
– volume: 56
  start-page: 101707
  year: 2020
  ident: 10.1016/j.bspc.2019.101707
  publication-title: Biomedical Signal Processing and Control
  doi: 10.1016/j.bspc.2019.101707
– volume: 182
  start-page: 115175
  year: 2021
  ident: 10.1016/j.eswa.2021.115175
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2021.115175
– volume: 15
  start-page: 111
  year: 2023
  ident: 10.20895/infotel.v15i1.874
  publication-title: JURNAL INFOTEL
  doi: 10.20895/infotel.v15i1.874
– volume: 41
  start-page: 670
  year: 2017
  ident: 10.1080/03091902.2017.1394388
  publication-title: Journal of Medical Engineering & Technology
  doi: 10.1080/03091902.2017.1394388
– volume: 17
  start-page: 3
  year: 2017
  ident: 10.4316/AECE.2017.04001
  publication-title: Advances in Electrical and Computer Engineering
  doi: 10.4316/AECE.2017.04001
– volume: 31
  start-page: 895
  year: 2021
  ident: 10.1002/ima.22565
  publication-title: International Journal of Imaging Systems and Technology
  doi: 10.1002/ima.22565
– volume: 134
  start-page: 840
  year: 2021
  ident: 10.1016/j.amjmed.2021.01.038
  publication-title: The American Journal of Medicine
  doi: 10.1016/j.amjmed.2021.01.038
– start-page: 1
  year: 2016
  ident: 10.1109/ICEDSA.2016.7818505
– volume: 2023
  start-page: 375
  year: 2023
  ident: 10.59277/ROMJIST.2023.3-4.10
  publication-title: Romanian Journal of Information Science and Technology
  doi: 10.59277/ROMJIST.2023.3-4.10
– volume: 126
  start-page: 4521
  year: 2023
  ident: 10.1007/s00170-023-11280-w
  publication-title: The International Journal of Advanced Manufacturing Technology
  doi: 10.1007/s00170-023-11280-w
– volume: 25
  start-page: 239
  year: 2022
  ident: 10.2339/politeknik.672077
  publication-title: Politeknik Dergisi
  doi: 10.2339/politeknik.672077
– start-page: 749
  year: 2016
  ident: 10.1109/ICASSP.2016.7471775
– volume: 28
  start-page: 1255
  year: 2025
  ident: 10.2339/politeknik.1605362
  publication-title: Politeknik Dergisi
  doi: 10.2339/politeknik.1605362
– volume: 67
  start-page: 140
  year: 2017
  ident: 10.1016/j.eswa.2016.09.037
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2016.09.037
– volume: 67
  start-page: 101943
  year: 2023
  ident: 10.1016/j.jocs.2023.101943
  publication-title: Journal of Computational Science
  doi: 10.1016/j.jocs.2023.101943
– volume: 152
  start-page: 349
  year: 2019
  ident: 10.1016/j.procs.2019.05.007
  publication-title: Procedia Computer Science
  doi: 10.1016/j.procs.2019.05.007
– volume: 8
  start-page: 16
  year: 2023
  ident: 10.52876/jcs.1226579
  publication-title: The Journal of Cognitive Systems
  doi: 10.52876/jcs.1226579
– volume: 11
  start-page: 2
  year: 2021
  ident: 10.1038/s41598-021-83337-3
  publication-title: Scientific Reports
  doi: 10.1038/s41598-021-83337-3
– volume: 64
  start-page: 352
  year: 2001
  ident: 10.1103/PhysRevE.64.061907
  publication-title: Physical Review E
  doi: 10.1103/PhysRevE.64.061907
– volume: 82
  start-page: 100
  year: 2017
  ident: 10.1016/j.compbiomed.2017.01.017
  publication-title: Computers in Biology and Medicine
  doi: 10.1016/j.compbiomed.2017.01.017
– volume: 30
  start-page: 1793
  year: 2019
  ident: 10.1007/s11045-018-0628-7
  publication-title: Multidimensional Systems and Signal Processing
  doi: 10.1007/s11045-018-0628-7
– start-page: 435
  year: 2008
  ident: 10.1109/BMEI.2008.254
– volume: 40
  start-page: 982
  year: 2018
  ident: 10.1080/01616412.2018.1508544
  publication-title: Neurological Research
  doi: 10.1080/01616412.2018.1508544
– volume: 96
  start-page: 103975
  year: 2020
  ident: 10.1016/j.engappai.2020.103975
  publication-title: Engineering Applications of Artificial Intelligence
  doi: 10.1016/j.engappai.2020.103975
– volume: 44
  start-page: 63
  year: 2012
  ident: 10.1007/s11062-012-9268-y
  publication-title: Neurophysiology
  doi: 10.1007/s11062-012-9268-y
– volume: 48
  start-page: 50
  year: 2009
  ident: 10.1016/j.neuroimage.2009.06.057
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2009.06.057
– volume: 148
  start-page: 746
  year: 2025
  ident: 10.1093/brain/awae385
  publication-title: Brain
  doi: 10.1093/brain/awae385
– start-page: 3386
  year: 2014
  ident: 10.1109/ICPR.2014.583
– volume: 180
  start-page: 298
  year: 2024
  ident: 10.1016/j.neurol.2023.12.005
  publication-title: Revue Neurologique
  doi: 10.1016/j.neurol.2023.12.005
– volume: 64
  start-page: 102005
  year: 2025
  ident: 10.1016/j.jestch.2025.102005
  publication-title: Engineering Science and Technology, an International Journal
  doi: 10.1016/j.jestch.2025.102005
– volume: 27
  start-page: 587
  year: 2024
  ident: 10.2339/politeknik.1055549
  publication-title: Politeknik Dergisi
  doi: 10.2339/politeknik.1055549
– volume: 5
  start-page: 147
  year: 2018
  ident: 10.1186/s40708-018-0084-z
  publication-title: Brain Informatics
  doi: 10.1186/s40708-018-0084-z
– volume: 25
  start-page: 399
  year: 2017
  ident: 10.3233/THC-171343
  publication-title: Technology and Health Care
  doi: 10.3233/THC-171343
– volume: 69
  start-page: 3120
  year: 2023
  ident: 10.1080/03772063.2021.1913074
  publication-title: IETE Journal of Research
  doi: 10.1080/03772063.2021.1913074
– volume: 13
  start-page: 703
  year: 2009
  ident: 10.1109/TITB.2009.2017939
  publication-title: IEEE Transactions on Information Technology in Biomedicine
  doi: 10.1109/TITB.2009.2017939
– volume: 84
  start-page: 146
  year: 2018
  ident: 10.1016/j.artmed.2017.12.004
  publication-title: Artificial Intelligence in Medicine
  doi: 10.1016/j.artmed.2017.12.004
SSID ssib044728236
ssib057620034
ssj0000395691
Score 2.3371835
Snippet Epileptic seizure detection is crucial for accurate diagnosis and effective treatment of epilepsy. Automated systems based on electroencephalogram signals play...
SourceID doaj
gale
crossref
SourceType Open Website
Aggregation Database
Index Database
StartPage 45
SubjectTerms Algorithms
Analysis
biomedical signal processing
Care and treatment
Comparative analysis
decision support systems
Diagnosis
Electroencephalography
Epilepsy
feature extraction
machine learning
Methods
Physiological aspects
Signal processing
Title The Impact of Feature Selection on Epilepsy Diagnosis from EEG Signals: A Comparison of Dynamic Time Warping and Itakura-Saito Distance
URI https://doaj.org/article/f84cae0c029342f79b5ae99eb3b3bcab
Volume 25
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1844-7600
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000395691
  issn: 1582-7445
  databaseCode: DOA
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1844-7600
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044728236
  issn: 1582-7445
  databaseCode: M~E
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1844-7600
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000395691
  issn: 1582-7445
  databaseCode: P5Z
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 1844-7600
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000395691
  issn: 1582-7445
  databaseCode: M7S
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1844-7600
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000395691
  issn: 1582-7445
  databaseCode: BENPR
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQxQEOiKdYKMgHJLiEuo7j2NyWbQo9UCEtiN6s8cRBq0rbVXYXqZde-dvMxNtVOHFBiSLlIcv2zNgz0cz3CfGGC3lM0liUnUuF8egLV7Zl0enSpmjQHEMmm6jPz93Fhf86ovrinLAMD5wn7qhzBiEpVLQvGd3VPlaQvKcYkA6EyKuvqv0omCJNMqbWt0zefE9ONSdhmf3fF1VSXOAzmCq7mMZUGfeHK8OPps2sodBRV-_JBJgLabRlDcj-u_V7tBOdPhQPdi6knOauPxJ30vKxuD8CFnwifpP05dlQACmvOsl-3rZPcj6Q3pAkJJ3NihaE1fpanuRsu8Vacq2JbJpPcr74ybjKH-RUzvZEhdzSSSawl1w5In9Az9VWEpatPNvA5baHYg60RFCT7HRieiq-nzbfZp-LHeVCgdpZW4B3xpl4nGLbIvkmqBGwI4mpaKqIOkHtbapsa5nzqrMOYxd9giqSHwIllM_EwfJqmZ4L2SJo1UbrSgXGoYrKY4U-kcfWkt3riXh3O6thlZE1AkUkLIDAAggsgDAIYCI-8qzvP2NI7OEBKUrYKUr4l6JMxFuWWWDD3fRA48r1B9RbhsAKU2cN11PVZiIO__qSDA5Hr1_8j968FPd4fDmV8FAcbPpteiXu4q_NYt2_HpSZrl9umj-qjfXz
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=The+Impact+of+Feature+Selection+on+Epilepsy+Diagnosis+from+EEG+Signals%3A+A+Comparison+of+Dynamic+Time+Warping+and+Itakura-Saito+Distance&rft.jtitle=Advances+in+electrical+and+computer+engineering&rft.au=EKIM%2C+G.&rft.au=IKIZLER%2C+N.&rft.date=2025-08-01&rft.issn=1582-7445&rft.eissn=1844-7600&rft.volume=25&rft.issue=3&rft.spage=45&rft.epage=58&rft_id=info:doi/10.4316%2FAECE.2025.03006&rft.externalDBID=n%2Fa&rft.externalDocID=10_4316_AECE_2025_03006
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1582-7445&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1582-7445&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1582-7445&client=summon