Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3

The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely dep...

Full description

Saved in:
Bibliographic Details
Published in:Cluster computing 2023-12, Vol.26 (6), p.3985-3995
Main Authors: Khasawneh, Natheer, Fraiwan, Mohammad, Fraiwan, Luay
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Boxes
Classification
Computer Communication Networks
Computer Science
Datasets
Deep learning
Electroencephalography
Epilepsy
Feature extraction
Inspection
Learning
Neural networks
Object recognition
Operating Systems
Performance evaluation
Processor Architectures
Restless legs syndrome
Signal analysis
Signal processing
Sleep
Support vector machines
Waveforms
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13
cites cdi_FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13
container_end_page 3995
container_issue 6
container_start_page 3985
container_title Cluster computing
container_volume 26
creator Khasawneh, Natheer
Fraiwan, Mohammad
Fraiwan, Luay
description The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection.
doi_str_mv 10.1007/s10586-022-03802-0
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2918257463</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2918257463</sourcerecordid><originalsourceid>FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13</originalsourceid><addsrcrecordid>eNp9UE1LAzEQDaJgrf4BTwHP0UmyaTZHqbWKhb3owVPYj0nZ0mbXZCv675u6gjcvM29m3nsMj5BrDrccQN9FDiqfMRCCgcwh1RMy4UpLplUmTxOW6axzpc_JRYwbADBamAkpHnDAemg7TztHX1jd7fotfmGkraeLxZLGdu3LbaT72Po1bRB7OoTSR4eBbrEM_rgufUPfi1XxKS_JmUt0vPrtU_L2uHidP7FVsXye369YLbkZmNaV0a6BMjPQuJJnTa1nGoRRRtbcSVkJlRmdo6wU6iYzjXKQJkyIy4rLKbkZffvQfewxDnbT7cPxUysMz4XS2UwmlhhZdehiDOhsH9pdGb4tB3sMzo7B2RSc_Qku1SmRoygmsl9j-LP-R3UA-cdu-A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2918257463</pqid></control><display><type>article</type><title>Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3</title><source>Springer Link</source><creator>Khasawneh, Natheer ; Fraiwan, Mohammad ; Fraiwan, Luay</creator><creatorcontrib>Khasawneh, Natheer ; Fraiwan, Mohammad ; Fraiwan, Luay</creatorcontrib><description>The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection.</description><identifier>ISSN: 1386-7857</identifier><identifier>EISSN: 1573-7543</identifier><identifier>DOI: 10.1007/s10586-022-03802-0</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Artificial intelligence ; Artificial neural networks ; Boxes ; Classification ; Computer Communication Networks ; Computer Science ; Datasets ; Deep learning ; Electroencephalography ; Epilepsy ; Feature extraction ; Inspection ; Learning ; Neural networks ; Object recognition ; Operating Systems ; Performance evaluation ; Processor Architectures ; Restless legs syndrome ; Signal analysis ; Signal processing ; Sleep ; Support vector machines ; Waveforms ; Wavelet transforms</subject><ispartof>Cluster computing, 2023-12, Vol.26 (6), p.3985-3995</ispartof><rights>The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13</citedby><cites>FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids></links><search><creatorcontrib>Khasawneh, Natheer</creatorcontrib><creatorcontrib>Fraiwan, Mohammad</creatorcontrib><creatorcontrib>Fraiwan, Luay</creatorcontrib><title>Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3</title><title>Cluster computing</title><addtitle>Cluster Comput</addtitle><description>The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection.</description><subject>Artificial intelligence</subject><subject>Artificial neural networks</subject><subject>Boxes</subject><subject>Classification</subject><subject>Computer Communication Networks</subject><subject>Computer Science</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Electroencephalography</subject><subject>Epilepsy</subject><subject>Feature extraction</subject><subject>Inspection</subject><subject>Learning</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Operating Systems</subject><subject>Performance evaluation</subject><subject>Processor Architectures</subject><subject>Restless legs syndrome</subject><subject>Signal analysis</subject><subject>Signal processing</subject><subject>Sleep</subject><subject>Support vector machines</subject><subject>Waveforms</subject><subject>Wavelet transforms</subject><issn>1386-7857</issn><issn>1573-7543</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9UE1LAzEQDaJgrf4BTwHP0UmyaTZHqbWKhb3owVPYj0nZ0mbXZCv675u6gjcvM29m3nsMj5BrDrccQN9FDiqfMRCCgcwh1RMy4UpLplUmTxOW6axzpc_JRYwbADBamAkpHnDAemg7TztHX1jd7fotfmGkraeLxZLGdu3LbaT72Po1bRB7OoTSR4eBbrEM_rgufUPfi1XxKS_JmUt0vPrtU_L2uHidP7FVsXye369YLbkZmNaV0a6BMjPQuJJnTa1nGoRRRtbcSVkJlRmdo6wU6iYzjXKQJkyIy4rLKbkZffvQfewxDnbT7cPxUysMz4XS2UwmlhhZdehiDOhsH9pdGb4tB3sMzo7B2RSc_Qku1SmRoygmsl9j-LP-R3UA-cdu-A</recordid><startdate>20231201</startdate><enddate>20231201</enddate><creator>Khasawneh, Natheer</creator><creator>Fraiwan, Mohammad</creator><creator>Fraiwan, Luay</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope></search><sort><creationdate>20231201</creationdate><title>Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3</title><author>Khasawneh, Natheer ; Fraiwan, Mohammad ; Fraiwan, Luay</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Artificial neural networks</topic><topic>Boxes</topic><topic>Classification</topic><topic>Computer Communication Networks</topic><topic>Computer Science</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Electroencephalography</topic><topic>Epilepsy</topic><topic>Feature extraction</topic><topic>Inspection</topic><topic>Learning</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Operating Systems</topic><topic>Performance evaluation</topic><topic>Processor Architectures</topic><topic>Restless legs syndrome</topic><topic>Signal analysis</topic><topic>Signal processing</topic><topic>Sleep</topic><topic>Support vector machines</topic><topic>Waveforms</topic><topic>Wavelet transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Khasawneh, Natheer</creatorcontrib><creatorcontrib>Fraiwan, Mohammad</creatorcontrib><creatorcontrib>Fraiwan, Luay</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>Cluster computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Khasawneh, Natheer</au><au>Fraiwan, Mohammad</au><au>Fraiwan, Luay</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3</atitle><jtitle>Cluster computing</jtitle><stitle>Cluster Comput</stitle><date>2023-12-01</date><risdate>2023</risdate><volume>26</volume><issue>6</issue><spage>3985</spage><epage>3995</epage><pages>3985-3995</pages><issn>1386-7857</issn><eissn>1573-7543</eissn><abstract>The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s10586-022-03802-0</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1386-7857
ispartof Cluster computing, 2023-12, Vol.26 (6), p.3985-3995
issn 1386-7857
1573-7543
language eng
recordid cdi_proquest_journals_2918257463
source Springer Link
subjects Artificial intelligence
Artificial neural networks
Boxes
Classification
Computer Communication Networks
Computer Science
Datasets
Deep learning
Electroencephalography
Epilepsy
Feature extraction
Inspection
Learning
Neural networks
Object recognition
Operating Systems
Performance evaluation
Processor Architectures
Restless legs syndrome
Signal analysis
Signal processing
Sleep
Support vector machines
Waveforms
Wavelet transforms
title Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T23%3A29%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Detection%20of%20K-complexes%20in%20EEG%20signals%20using%20deep%20transfer%20learning%20and%20YOLOv3&rft.jtitle=Cluster%20computing&rft.au=Khasawneh,%20Natheer&rft.date=2023-12-01&rft.volume=26&rft.issue=6&rft.spage=3985&rft.epage=3995&rft.pages=3985-3995&rft.issn=1386-7857&rft.eissn=1573-7543&rft_id=info:doi/10.1007/s10586-022-03802-0&rft_dat=%3Cproquest_cross%3E2918257463%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c319t-77b97fd0a490dfa14dc767029593c1f33b254978e3b5e7d49d5f08e3e49d13b13%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2918257463&rft_id=info:pmid/&rfr_iscdi=true