Loading…
EEG SOURCE LOCALIZATION: A COMPARATIVE STUDY OF CLASSICAL AND NEURAL NETWORK METHODS
We address the problem of estimating biopotential sources within the brain, based on EEG signals observed on the scalp. This problem, known as the inverse problem of electrophysiology, has no closed-form solution, and requires iterative techniques such as the Levenberg – Marquardt (LM) algorithm. Co...
Saved in:
| Published in: | International journal of neural systems 2001-08, Vol.11 (4), p.349-359 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | 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-c3483-4baa7ebc495ca23e4530d88420f3e838a9dbdf4d6600dd9e25bd7f18bb1b2cd63 |
|---|---|
| cites | |
| container_end_page | 359 |
| container_issue | 4 |
| container_start_page | 349 |
| container_title | International journal of neural systems |
| container_volume | 11 |
| creator | ABEYRATNE, UDANTHA R. ZHANG, G. SARATCHANDRAN, P. |
| description | We address the problem of estimating biopotential sources within the
brain, based on EEG signals observed on the scalp. This problem, known
as the inverse problem of electrophysiology, has no closed-form
solution, and requires iterative techniques such as the Levenberg –
Marquardt (LM) algorithm. Considering the nonlinear nature of the
inverse problem, and the low signal to noise ratio inherent in EEG
signals, a backpropagation neural network (BPN) has been recently
proposed as a solution. The technique has not been properly compared
with classical techniques such as the LM method, or with more recent
neural network techniques such as the Radial Basis Function (RBF)
network. In this paper, we provide improved strategies based on BPN
and consider RBF networks in solving the inverse problem. We compare
the performances of BPN, RBF and a hybrid technique with that of the
classical LM method. |
| doi_str_mv | 10.1142/S0129065701000813 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmed_primary_11706410</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>72276466</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3483-4baa7ebc495ca23e4530d88420f3e838a9dbdf4d6600dd9e25bd7f18bb1b2cd63</originalsourceid><addsrcrecordid>eNplkMtOg0AUhidGY2v1AdyYWblDz1y4uSOUXiIFw0WjGwLMkGBoqUwb49sLaaOLrs45Od__Lz6Ebgk8EMLpYwyE2mDoJhAAsAg7Q2Ni2kwzuEHP0Xh4a8N_hK6U-gQg3OTWJRoRYoLBCYxR4nlzHIdp5HrYD13HX344yTIMnrCD3XD14kT9-erhOEmn7zicYdd34njZg9gJpjjw0qhfAy95C6NnvPKSRTiNr9FFlTdK3hznBKUzL3EXmh_Oh6hWMm4xjRd5bsqi5LZe5pRJrjMQlsUpVExazMptUYiKC8MAEMKWVC-EWRGrKEhBS2GwCbo_9G679msv1S5b16qUTZNvZLtXmUmp2asYQHIAy65VqpNVtu3qdd79ZASyQWV2orLP3B3L98Vaiv_E0V0PwAH4brtGqLKWm11d1eUfedr5C3Ecdg4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>72276466</pqid></control><display><type>article</type><title>EEG SOURCE LOCALIZATION: A COMPARATIVE STUDY OF CLASSICAL AND NEURAL NETWORK METHODS</title><source>TRIAL: World Scientific Journals</source><creator>ABEYRATNE, UDANTHA R. ; ZHANG, G. ; SARATCHANDRAN, P.</creator><creatorcontrib>ABEYRATNE, UDANTHA R. ; ZHANG, G. ; SARATCHANDRAN, P.</creatorcontrib><description>We address the problem of estimating biopotential sources within the
brain, based on EEG signals observed on the scalp. This problem, known
as the inverse problem of electrophysiology, has no closed-form
solution, and requires iterative techniques such as the Levenberg –
Marquardt (LM) algorithm. Considering the nonlinear nature of the
inverse problem, and the low signal to noise ratio inherent in EEG
signals, a backpropagation neural network (BPN) has been recently
proposed as a solution. The technique has not been properly compared
with classical techniques such as the LM method, or with more recent
neural network techniques such as the Radial Basis Function (RBF)
network. In this paper, we provide improved strategies based on BPN
and consider RBF networks in solving the inverse problem. We compare
the performances of BPN, RBF and a hybrid technique with that of the
classical LM method.</description><identifier>ISSN: 0129-0657</identifier><identifier>EISSN: 1793-6462</identifier><identifier>DOI: 10.1142/S0129065701000813</identifier><identifier>PMID: 11706410</identifier><language>eng</language><publisher>Singapore: World Scientific Publishing Company</publisher><subject>Brain - physiology ; Brain - physiopathology ; Electroencephalography - methods ; Humans ; Neural Networks (Computer)</subject><ispartof>International journal of neural systems, 2001-08, Vol.11 (4), p.349-359</ispartof><rights>2001, World Scientific Publishing Company</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3483-4baa7ebc495ca23e4530d88420f3e838a9dbdf4d6600dd9e25bd7f18bb1b2cd63</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.worldscientific.com/doi/reader/10.1142/S0129065701000813$$EPDF$$P50$$Gworldscientific$$H</linktopdf><link.rule.ids>314,780,784,3211,4870,27922,27923,55585</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/11706410$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>ABEYRATNE, UDANTHA R.</creatorcontrib><creatorcontrib>ZHANG, G.</creatorcontrib><creatorcontrib>SARATCHANDRAN, P.</creatorcontrib><title>EEG SOURCE LOCALIZATION: A COMPARATIVE STUDY OF CLASSICAL AND NEURAL NETWORK METHODS</title><title>International journal of neural systems</title><addtitle>Int J Neural Syst</addtitle><description>We address the problem of estimating biopotential sources within the
brain, based on EEG signals observed on the scalp. This problem, known
as the inverse problem of electrophysiology, has no closed-form
solution, and requires iterative techniques such as the Levenberg –
Marquardt (LM) algorithm. Considering the nonlinear nature of the
inverse problem, and the low signal to noise ratio inherent in EEG
signals, a backpropagation neural network (BPN) has been recently
proposed as a solution. The technique has not been properly compared
with classical techniques such as the LM method, or with more recent
neural network techniques such as the Radial Basis Function (RBF)
network. In this paper, we provide improved strategies based on BPN
and consider RBF networks in solving the inverse problem. We compare
the performances of BPN, RBF and a hybrid technique with that of the
classical LM method.</description><subject>Brain - physiology</subject><subject>Brain - physiopathology</subject><subject>Electroencephalography - methods</subject><subject>Humans</subject><subject>Neural Networks (Computer)</subject><issn>0129-0657</issn><issn>1793-6462</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2001</creationdate><recordtype>article</recordtype><recordid>eNplkMtOg0AUhidGY2v1AdyYWblDz1y4uSOUXiIFw0WjGwLMkGBoqUwb49sLaaOLrs45Od__Lz6Ebgk8EMLpYwyE2mDoJhAAsAg7Q2Ni2kwzuEHP0Xh4a8N_hK6U-gQg3OTWJRoRYoLBCYxR4nlzHIdp5HrYD13HX344yTIMnrCD3XD14kT9-erhOEmn7zicYdd34njZg9gJpjjw0qhfAy95C6NnvPKSRTiNr9FFlTdK3hznBKUzL3EXmh_Oh6hWMm4xjRd5bsqi5LZe5pRJrjMQlsUpVExazMptUYiKC8MAEMKWVC-EWRGrKEhBS2GwCbo_9G679msv1S5b16qUTZNvZLtXmUmp2asYQHIAy65VqpNVtu3qdd79ZASyQWV2orLP3B3L98Vaiv_E0V0PwAH4brtGqLKWm11d1eUfedr5C3Ecdg4</recordid><startdate>200108</startdate><enddate>200108</enddate><creator>ABEYRATNE, UDANTHA R.</creator><creator>ZHANG, G.</creator><creator>SARATCHANDRAN, P.</creator><general>World Scientific Publishing Company</general><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></search><sort><creationdate>200108</creationdate><title>EEG SOURCE LOCALIZATION: A COMPARATIVE STUDY OF CLASSICAL AND NEURAL NETWORK METHODS</title><author>ABEYRATNE, UDANTHA R. ; ZHANG, G. ; SARATCHANDRAN, P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3483-4baa7ebc495ca23e4530d88420f3e838a9dbdf4d6600dd9e25bd7f18bb1b2cd63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2001</creationdate><topic>Brain - physiology</topic><topic>Brain - physiopathology</topic><topic>Electroencephalography - methods</topic><topic>Humans</topic><topic>Neural Networks (Computer)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>ABEYRATNE, UDANTHA R.</creatorcontrib><creatorcontrib>ZHANG, G.</creatorcontrib><creatorcontrib>SARATCHANDRAN, P.</creatorcontrib><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>International journal of neural systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>ABEYRATNE, UDANTHA R.</au><au>ZHANG, G.</au><au>SARATCHANDRAN, P.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EEG SOURCE LOCALIZATION: A COMPARATIVE STUDY OF CLASSICAL AND NEURAL NETWORK METHODS</atitle><jtitle>International journal of neural systems</jtitle><addtitle>Int J Neural Syst</addtitle><date>2001-08</date><risdate>2001</risdate><volume>11</volume><issue>4</issue><spage>349</spage><epage>359</epage><pages>349-359</pages><issn>0129-0657</issn><eissn>1793-6462</eissn><abstract>We address the problem of estimating biopotential sources within the
brain, based on EEG signals observed on the scalp. This problem, known
as the inverse problem of electrophysiology, has no closed-form
solution, and requires iterative techniques such as the Levenberg –
Marquardt (LM) algorithm. Considering the nonlinear nature of the
inverse problem, and the low signal to noise ratio inherent in EEG
signals, a backpropagation neural network (BPN) has been recently
proposed as a solution. The technique has not been properly compared
with classical techniques such as the LM method, or with more recent
neural network techniques such as the Radial Basis Function (RBF)
network. In this paper, we provide improved strategies based on BPN
and consider RBF networks in solving the inverse problem. We compare
the performances of BPN, RBF and a hybrid technique with that of the
classical LM method.</abstract><cop>Singapore</cop><pub>World Scientific Publishing Company</pub><pmid>11706410</pmid><doi>10.1142/S0129065701000813</doi><tpages>11</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0129-0657 |
| ispartof | International journal of neural systems, 2001-08, Vol.11 (4), p.349-359 |
| issn | 0129-0657 1793-6462 |
| language | eng |
| recordid | cdi_pubmed_primary_11706410 |
| source | TRIAL: World Scientific Journals |
| subjects | Brain - physiology Brain - physiopathology Electroencephalography - methods Humans Neural Networks (Computer) |
| title | EEG SOURCE LOCALIZATION: A COMPARATIVE STUDY OF CLASSICAL AND NEURAL NETWORK METHODS |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T12%3A25%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=EEG%20SOURCE%20LOCALIZATION:%20A%20COMPARATIVE%20STUDY%20OF%20CLASSICAL%20AND%20NEURAL%20NETWORK%20METHODS&rft.jtitle=International%20journal%20of%20neural%20systems&rft.au=ABEYRATNE,%20UDANTHA%20R.&rft.date=2001-08&rft.volume=11&rft.issue=4&rft.spage=349&rft.epage=359&rft.pages=349-359&rft.issn=0129-0657&rft.eissn=1793-6462&rft_id=info:doi/10.1142/S0129065701000813&rft_dat=%3Cproquest_pubme%3E72276466%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c3483-4baa7ebc495ca23e4530d88420f3e838a9dbdf4d6600dd9e25bd7f18bb1b2cd63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=72276466&rft_id=info:pmid/11706410&rfr_iscdi=true |