SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification
In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neigh...
Gespeichert in:
| Veröffentlicht in: | IEEE transaction on neural networks and learning systems 2024-09, Vol.35 (9), p.12157-12171 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 12171 |
|---|---|
| container_issue | 9 |
| container_start_page | 12157 |
| container_title | IEEE transaction on neural networks and learning systems |
| container_volume | 35 |
| creator | Wang, Jialin Gao, Rui Zheng, Haotian Zhu, Hao Shi, C.-J. Richard |
| description | In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller. |
| doi_str_mv | 10.1109/TNNLS.2023.3252569 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10075361</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10075361</ieee_id><sourcerecordid>2798714170</sourcerecordid><originalsourceid>FETCH-LOGICAL-c368t-a7610e90bbe8af6238350122d0477a582a5c96604969f002ca36cb7c53768e7c3</originalsourceid><addsrcrecordid>eNpNkF1LwzAUhoMobsz9ARHJpTed-WiTxrtRahXGvOgEbySkWarRbq1Jq_jvbd0cnptzLp73hfMAcI7RDGMkrlfL5SKfEUTojJKIREwcgTHBjASExvHx4eZPIzD1_g31w1DEQnEKRpQjijgRY_Cc51myNO0NnMO8Uc6bfhndOgUzp5pXmNTbz7rqWltvVQV78qt277CsHUwbW5mmtRqmaQZz-zIASaW8t6XVakicgZNSVd5M93sCHm_TVXIXLB6y-2S-CDRlcRsozjAyAhWFiVXJ-gdohDAhaxRyrqKYqEgLxlAomCgRIlpRpguuI8pZbLimE3C1621c_dEZ38qN9dpUldqauvOScBFzHOL-7QkgO1S72ntnStk4u1HuW2IkB7Py16wczMq92T50ue_vio1ZHyJ_HnvgYgdYY8y_RsQjyjD9Aa83e2A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2798714170</pqid></control><display><type>article</type><title>SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification</title><source>MEDLINE</source><source>IEEE Electronic Library (IEL)</source><creator>Wang, Jialin ; Gao, Rui ; Zheng, Haotian ; Zhu, Hao ; Shi, C.-J. Richard</creator><creatorcontrib>Wang, Jialin ; Gao, Rui ; Zheng, Haotian ; Zhu, Hao ; Shi, C.-J. Richard</creatorcontrib><description>In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller.</description><identifier>ISSN: 2162-237X</identifier><identifier>ISSN: 2162-2388</identifier><identifier>EISSN: 2162-2388</identifier><identifier>DOI: 10.1109/TNNLS.2023.3252569</identifier><identifier>PMID: 37030729</identifier><identifier>CODEN: ITNNAL</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Algorithms ; Alternating direction method of multipliers (ADMM) ; Brain modeling ; Computational modeling ; Convolutional neural networks ; Deep Learning ; electroencephalogram (EEG) signal classification ; Electroencephalography ; Electroencephalography - classification ; Electroencephalography - methods ; Epilepsy - classification ; Epilepsy - diagnosis ; Epilepsy - physiopathology ; Feature extraction ; graph neural network (GNN) ; Humans ; Neural Networks, Computer ; nonconvextiy ; Pattern classification ; Signal Processing, Computer-Assisted ; weight pruning</subject><ispartof>IEEE transaction on neural networks and learning systems, 2024-09, Vol.35 (9), p.12157-12171</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c368t-a7610e90bbe8af6238350122d0477a582a5c96604969f002ca36cb7c53768e7c3</citedby><cites>FETCH-LOGICAL-c368t-a7610e90bbe8af6238350122d0477a582a5c96604969f002ca36cb7c53768e7c3</cites><orcidid>0000-0002-3157-3464 ; 0000-0003-4202-9656 ; 0000-0001-7570-8140 ; 0009-0001-0791-7108</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10075361$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,777,781,793,27905,27906,54739</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37030729$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Jialin</creatorcontrib><creatorcontrib>Gao, Rui</creatorcontrib><creatorcontrib>Zheng, Haotian</creatorcontrib><creatorcontrib>Zhu, Hao</creatorcontrib><creatorcontrib>Shi, C.-J. Richard</creatorcontrib><title>SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification</title><title>IEEE transaction on neural networks and learning systems</title><addtitle>TNNLS</addtitle><addtitle>IEEE Trans Neural Netw Learn Syst</addtitle><description>In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller.</description><subject>Algorithms</subject><subject>Alternating direction method of multipliers (ADMM)</subject><subject>Brain modeling</subject><subject>Computational modeling</subject><subject>Convolutional neural networks</subject><subject>Deep Learning</subject><subject>electroencephalogram (EEG) signal classification</subject><subject>Electroencephalography</subject><subject>Electroencephalography - classification</subject><subject>Electroencephalography - methods</subject><subject>Epilepsy - classification</subject><subject>Epilepsy - diagnosis</subject><subject>Epilepsy - physiopathology</subject><subject>Feature extraction</subject><subject>graph neural network (GNN)</subject><subject>Humans</subject><subject>Neural Networks, Computer</subject><subject>nonconvextiy</subject><subject>Pattern classification</subject><subject>Signal Processing, Computer-Assisted</subject><subject>weight pruning</subject><issn>2162-237X</issn><issn>2162-2388</issn><issn>2162-2388</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNpNkF1LwzAUhoMobsz9ARHJpTed-WiTxrtRahXGvOgEbySkWarRbq1Jq_jvbd0cnptzLp73hfMAcI7RDGMkrlfL5SKfEUTojJKIREwcgTHBjASExvHx4eZPIzD1_g31w1DEQnEKRpQjijgRY_Cc51myNO0NnMO8Uc6bfhndOgUzp5pXmNTbz7rqWltvVQV78qt277CsHUwbW5mmtRqmaQZz-zIASaW8t6XVakicgZNSVd5M93sCHm_TVXIXLB6y-2S-CDRlcRsozjAyAhWFiVXJ-gdohDAhaxRyrqKYqEgLxlAomCgRIlpRpguuI8pZbLimE3C1621c_dEZ38qN9dpUldqauvOScBFzHOL-7QkgO1S72ntnStk4u1HuW2IkB7Py16wczMq92T50ue_vio1ZHyJ_HnvgYgdYY8y_RsQjyjD9Aa83e2A</recordid><startdate>20240901</startdate><enddate>20240901</enddate><creator>Wang, Jialin</creator><creator>Gao, Rui</creator><creator>Zheng, Haotian</creator><creator>Zhu, Hao</creator><creator>Shi, C.-J. Richard</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-3157-3464</orcidid><orcidid>https://orcid.org/0000-0003-4202-9656</orcidid><orcidid>https://orcid.org/0000-0001-7570-8140</orcidid><orcidid>https://orcid.org/0009-0001-0791-7108</orcidid></search><sort><creationdate>20240901</creationdate><title>SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification</title><author>Wang, Jialin ; Gao, Rui ; Zheng, Haotian ; Zhu, Hao ; Shi, C.-J. Richard</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c368t-a7610e90bbe8af6238350122d0477a582a5c96604969f002ca36cb7c53768e7c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Alternating direction method of multipliers (ADMM)</topic><topic>Brain modeling</topic><topic>Computational modeling</topic><topic>Convolutional neural networks</topic><topic>Deep Learning</topic><topic>electroencephalogram (EEG) signal classification</topic><topic>Electroencephalography</topic><topic>Electroencephalography - classification</topic><topic>Electroencephalography - methods</topic><topic>Epilepsy - classification</topic><topic>Epilepsy - diagnosis</topic><topic>Epilepsy - physiopathology</topic><topic>Feature extraction</topic><topic>graph neural network (GNN)</topic><topic>Humans</topic><topic>Neural Networks, Computer</topic><topic>nonconvextiy</topic><topic>Pattern classification</topic><topic>Signal Processing, Computer-Assisted</topic><topic>weight pruning</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Jialin</creatorcontrib><creatorcontrib>Gao, Rui</creatorcontrib><creatorcontrib>Zheng, Haotian</creatorcontrib><creatorcontrib>Zhu, Hao</creatorcontrib><creatorcontrib>Shi, C.-J. Richard</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transaction on neural networks and learning systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Jialin</au><au>Gao, Rui</au><au>Zheng, Haotian</au><au>Zhu, Hao</au><au>Shi, C.-J. Richard</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification</atitle><jtitle>IEEE transaction on neural networks and learning systems</jtitle><stitle>TNNLS</stitle><addtitle>IEEE Trans Neural Netw Learn Syst</addtitle><date>2024-09-01</date><risdate>2024</risdate><volume>35</volume><issue>9</issue><spage>12157</spage><epage>12171</epage><pages>12157-12171</pages><issn>2162-237X</issn><issn>2162-2388</issn><eissn>2162-2388</eissn><coden>ITNNAL</coden><abstract>In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>37030729</pmid><doi>10.1109/TNNLS.2023.3252569</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-3157-3464</orcidid><orcidid>https://orcid.org/0000-0003-4202-9656</orcidid><orcidid>https://orcid.org/0000-0001-7570-8140</orcidid><orcidid>https://orcid.org/0009-0001-0791-7108</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2162-237X |
| ispartof | IEEE transaction on neural networks and learning systems, 2024-09, Vol.35 (9), p.12157-12171 |
| issn | 2162-237X 2162-2388 2162-2388 |
| language | eng |
| recordid | cdi_ieee_primary_10075361 |
| source | MEDLINE; IEEE Electronic Library (IEL) |
| subjects | Algorithms Alternating direction method of multipliers (ADMM) Brain modeling Computational modeling Convolutional neural networks Deep Learning electroencephalogram (EEG) signal classification Electroencephalography Electroencephalography - classification Electroencephalography - methods Epilepsy - classification Epilepsy - diagnosis Epilepsy - physiopathology Feature extraction graph neural network (GNN) Humans Neural Networks, Computer nonconvextiy Pattern classification Signal Processing, Computer-Assisted weight pruning |
| title | SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T05%3A25%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SSGCNet:%20A%20Sparse%20Spectra%20Graph%20Convolutional%20Network%20for%20Epileptic%20EEG%20Signal%20Classification&rft.jtitle=IEEE%20transaction%20on%20neural%20networks%20and%20learning%20systems&rft.au=Wang,%20Jialin&rft.date=2024-09-01&rft.volume=35&rft.issue=9&rft.spage=12157&rft.epage=12171&rft.pages=12157-12171&rft.issn=2162-237X&rft.eissn=2162-2388&rft.coden=ITNNAL&rft_id=info:doi/10.1109/TNNLS.2023.3252569&rft_dat=%3Cproquest_ieee_%3E2798714170%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2798714170&rft_id=info:pmid/37030729&rft_ieee_id=10075361&rfr_iscdi=true |