Loading…
EEG sensorimotor rhythms' variation and functional connectivity measures during motor imagery: linear relations and classification approaches
Hands motor imagery (MI) has been reported to alter synchronization patterns amongst neurons, yielding variations in the mu and beta bands' power spectral density (PSD) of the electroencephalography (EEG) signal. These alterations have been used in the field of brain-computer interfaces (BCI),...
Saved in:
| Published in: | PeerJ (San Francisco, CA) CA), 2017-11, Vol.5, p.e3983-e3983, Article e3983 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| 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-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793 |
| container_end_page | e3983 |
| container_issue | |
| container_start_page | e3983 |
| container_title | PeerJ (San Francisco, CA) |
| container_volume | 5 |
| creator | Stefano Filho, Carlos A Attux, Romis Castellano, Gabriela |
| description | Hands motor imagery (MI) has been reported to alter synchronization patterns amongst neurons, yielding variations in the mu and beta bands' power spectral density (PSD) of the electroencephalography (EEG) signal. These alterations have been used in the field of brain-computer interfaces (BCI), in an attempt to assign distinct MI tasks to commands of such a system. Recent studies have highlighted that information may be missing if knowledge about brain functional connectivity is not considered. In this work, we modeled the brain as a graph in which each EEG electrode represents a node. Our goal was to understand if there exists any linear correlation between variations in the synchronization patterns-that is, variations in the PSD of mu and beta bands-induced by MI and alterations in the corresponding functional networks. Moreover, we (1) explored the feasibility of using functional connectivity parameters as features for a classifier in the context of an MI-BCI; (2) investigated three different types of feature selection (FS) techniques; and (3) compared our approach to a more traditional method using the signal PSD as classifier inputs. Ten healthy subjects participated in this study. We observed significant correlations (
|
| doi_str_mv | 10.7717/peerj.3983 |
| format | article |
| fullrecord | <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_39dadb127be54bd580284f9364dbad19</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A513768090</galeid><doaj_id>oai_doaj_org_article_39dadb127be54bd580284f9364dbad19</doaj_id><sourcerecordid>A513768090</sourcerecordid><originalsourceid>FETCH-LOGICAL-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793</originalsourceid><addsrcrecordid>eNptktuKEzEYgAdR3GXdGx9ABgQVoWsOM5OMF8Ky1HVhwRu9DpnkTyclk9RkptCH8J1Np3VpxeQipy9fDv9fFK8xumEMs08bgLi-oS2nz4pLghu24LRun5_0L4rrlNYoF04axOnL4oK0mFa4opfF7-XyvkzgU4h2CGOIZex3Yz-k9-VWRitHG3wpvS7N5NV-IF2pgveQB1s77soBZJoipFJP0fpVeZDYQa4g7j6XznqQWQpuVqXZpZxMyRqrjvrNJgapekivihdGugTXx_aq-Pl1-ePu2-Lx-_3D3e3jQtUMjYuOIQIENdxwxXjTQE0URmCq3G01RQahjuBWI0Mk4pgzKmvFADVYd13NWnpVPBy8Osi12OSny7gTQVoxT4S4EjKOVjkQtNVSd5iwDuqq0zVHhFempU2lO6nx3vXl4NpM3QBagR-jdGfS8xVve7EKW1E3-Wo1zYIPR0EMvyZIoxhsUuCc9BCmJHDbVISRqq0y-vYfdB2mmGMyU5hRzGbhkVrJ_ADrTcjnqr1U3NaYsoajFmXq5j9UrhoGm0MMxub5sw3vTjb0IN3Yp-CmOa7n4McDqGJIKYJ5-gyMxD5pxZy0Yp-0GX5z-n1P6N8UpX8AmELpYA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1961731753</pqid></control><display><type>article</type><title>EEG sensorimotor rhythms' variation and functional connectivity measures during motor imagery: linear relations and classification approaches</title><source>Open Access: PubMed Central</source><source>ProQuest - Publicly Available Content Database</source><creator>Stefano Filho, Carlos A ; Attux, Romis ; Castellano, Gabriela</creator><creatorcontrib>Stefano Filho, Carlos A ; Attux, Romis ; Castellano, Gabriela</creatorcontrib><description>Hands motor imagery (MI) has been reported to alter synchronization patterns amongst neurons, yielding variations in the mu and beta bands' power spectral density (PSD) of the electroencephalography (EEG) signal. These alterations have been used in the field of brain-computer interfaces (BCI), in an attempt to assign distinct MI tasks to commands of such a system. Recent studies have highlighted that information may be missing if knowledge about brain functional connectivity is not considered. In this work, we modeled the brain as a graph in which each EEG electrode represents a node. Our goal was to understand if there exists any linear correlation between variations in the synchronization patterns-that is, variations in the PSD of mu and beta bands-induced by MI and alterations in the corresponding functional networks. Moreover, we (1) explored the feasibility of using functional connectivity parameters as features for a classifier in the context of an MI-BCI; (2) investigated three different types of feature selection (FS) techniques; and (3) compared our approach to a more traditional method using the signal PSD as classifier inputs. Ten healthy subjects participated in this study. We observed significant correlations (
< 0.05) with values ranging from 0.4 to 0.9 between PSD variations and functional network alterations for some electrodes, prominently in the beta band. The PSD method performed better for data classification, with mean accuracies of (90 ± 8)% and (87 ± 7)% for the mu and beta band, respectively, versus (83 ± 8)% and (83 ± 7)% for the same bands for the graph method. Moreover, the number of features for the graph method was considerably larger. However, results for both methods were relatively close, and even overlapped when the uncertainties of the accuracy rates were considered. Further investigation regarding a careful exploration of other graph metrics may provide better alternatives.</description><identifier>ISSN: 2167-8359</identifier><identifier>EISSN: 2167-8359</identifier><identifier>DOI: 10.7717/peerj.3983</identifier><identifier>PMID: 29134143</identifier><language>eng</language><publisher>United States: PeerJ. Ltd</publisher><subject>Analysis ; BCI ; Biomedical engineering ; Brain-computer interface ; Classification ; Computational Science ; Computer engineering ; EEG ; Electrodes ; Electroencephalography ; Emulation ; Fourier transforms ; Hands ; Human-Computer Interaction ; Interfaces ; Localization (Brain function) ; Mental task performance ; Motor imagery ; Motor skills ; Neural networks ; Neurology ; Neuroscience ; Neurosciences ; Physiological aspects ; Rehabilitation ; Sensorimotor system ; Signal processing ; Spectrum analysis ; Studies ; Synchronization ; Variation</subject><ispartof>PeerJ (San Francisco, CA), 2017-11, Vol.5, p.e3983-e3983, Article e3983</ispartof><rights>COPYRIGHT 2017 PeerJ. Ltd.</rights><rights>2017 Stefano Filho et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2017 Stefano Filho et al. 2017 Stefano Filho et al.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793</citedby><cites>FETCH-LOGICAL-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/1961731753/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/1961731753?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,25752,27923,27924,37011,37012,44589,53790,53792,74897</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29134143$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Stefano Filho, Carlos A</creatorcontrib><creatorcontrib>Attux, Romis</creatorcontrib><creatorcontrib>Castellano, Gabriela</creatorcontrib><title>EEG sensorimotor rhythms' variation and functional connectivity measures during motor imagery: linear relations and classification approaches</title><title>PeerJ (San Francisco, CA)</title><addtitle>PeerJ</addtitle><description>Hands motor imagery (MI) has been reported to alter synchronization patterns amongst neurons, yielding variations in the mu and beta bands' power spectral density (PSD) of the electroencephalography (EEG) signal. These alterations have been used in the field of brain-computer interfaces (BCI), in an attempt to assign distinct MI tasks to commands of such a system. Recent studies have highlighted that information may be missing if knowledge about brain functional connectivity is not considered. In this work, we modeled the brain as a graph in which each EEG electrode represents a node. Our goal was to understand if there exists any linear correlation between variations in the synchronization patterns-that is, variations in the PSD of mu and beta bands-induced by MI and alterations in the corresponding functional networks. Moreover, we (1) explored the feasibility of using functional connectivity parameters as features for a classifier in the context of an MI-BCI; (2) investigated three different types of feature selection (FS) techniques; and (3) compared our approach to a more traditional method using the signal PSD as classifier inputs. Ten healthy subjects participated in this study. We observed significant correlations (
< 0.05) with values ranging from 0.4 to 0.9 between PSD variations and functional network alterations for some electrodes, prominently in the beta band. The PSD method performed better for data classification, with mean accuracies of (90 ± 8)% and (87 ± 7)% for the mu and beta band, respectively, versus (83 ± 8)% and (83 ± 7)% for the same bands for the graph method. Moreover, the number of features for the graph method was considerably larger. However, results for both methods were relatively close, and even overlapped when the uncertainties of the accuracy rates were considered. Further investigation regarding a careful exploration of other graph metrics may provide better alternatives.</description><subject>Analysis</subject><subject>BCI</subject><subject>Biomedical engineering</subject><subject>Brain-computer interface</subject><subject>Classification</subject><subject>Computational Science</subject><subject>Computer engineering</subject><subject>EEG</subject><subject>Electrodes</subject><subject>Electroencephalography</subject><subject>Emulation</subject><subject>Fourier transforms</subject><subject>Hands</subject><subject>Human-Computer Interaction</subject><subject>Interfaces</subject><subject>Localization (Brain function)</subject><subject>Mental task performance</subject><subject>Motor imagery</subject><subject>Motor skills</subject><subject>Neural networks</subject><subject>Neurology</subject><subject>Neuroscience</subject><subject>Neurosciences</subject><subject>Physiological aspects</subject><subject>Rehabilitation</subject><subject>Sensorimotor system</subject><subject>Signal processing</subject><subject>Spectrum analysis</subject><subject>Studies</subject><subject>Synchronization</subject><subject>Variation</subject><issn>2167-8359</issn><issn>2167-8359</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNptktuKEzEYgAdR3GXdGx9ABgQVoWsOM5OMF8Ky1HVhwRu9DpnkTyclk9RkptCH8J1Np3VpxeQipy9fDv9fFK8xumEMs08bgLi-oS2nz4pLghu24LRun5_0L4rrlNYoF04axOnL4oK0mFa4opfF7-XyvkzgU4h2CGOIZex3Yz-k9-VWRitHG3wpvS7N5NV-IF2pgveQB1s77soBZJoipFJP0fpVeZDYQa4g7j6XznqQWQpuVqXZpZxMyRqrjvrNJgapekivihdGugTXx_aq-Pl1-ePu2-Lx-_3D3e3jQtUMjYuOIQIENdxwxXjTQE0URmCq3G01RQahjuBWI0Mk4pgzKmvFADVYd13NWnpVPBy8Osi12OSny7gTQVoxT4S4EjKOVjkQtNVSd5iwDuqq0zVHhFempU2lO6nx3vXl4NpM3QBagR-jdGfS8xVve7EKW1E3-Wo1zYIPR0EMvyZIoxhsUuCc9BCmJHDbVISRqq0y-vYfdB2mmGMyU5hRzGbhkVrJ_ADrTcjnqr1U3NaYsoajFmXq5j9UrhoGm0MMxub5sw3vTjb0IN3Yp-CmOa7n4McDqGJIKYJ5-gyMxD5pxZy0Yp-0GX5z-n1P6N8UpX8AmELpYA</recordid><startdate>20171108</startdate><enddate>20171108</enddate><creator>Stefano Filho, Carlos A</creator><creator>Attux, Romis</creator><creator>Castellano, Gabriela</creator><general>PeerJ. Ltd</general><general>PeerJ, Inc</general><general>PeerJ Inc</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7XB</scope><scope>88I</scope><scope>8FE</scope><scope>8FH</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>LK8</scope><scope>M2P</scope><scope>M7P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20171108</creationdate><title>EEG sensorimotor rhythms' variation and functional connectivity measures during motor imagery: linear relations and classification approaches</title><author>Stefano Filho, Carlos A ; Attux, Romis ; Castellano, Gabriela</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Analysis</topic><topic>BCI</topic><topic>Biomedical engineering</topic><topic>Brain-computer interface</topic><topic>Classification</topic><topic>Computational Science</topic><topic>Computer engineering</topic><topic>EEG</topic><topic>Electrodes</topic><topic>Electroencephalography</topic><topic>Emulation</topic><topic>Fourier transforms</topic><topic>Hands</topic><topic>Human-Computer Interaction</topic><topic>Interfaces</topic><topic>Localization (Brain function)</topic><topic>Mental task performance</topic><topic>Motor imagery</topic><topic>Motor skills</topic><topic>Neural networks</topic><topic>Neurology</topic><topic>Neuroscience</topic><topic>Neurosciences</topic><topic>Physiological aspects</topic><topic>Rehabilitation</topic><topic>Sensorimotor system</topic><topic>Signal processing</topic><topic>Spectrum analysis</topic><topic>Studies</topic><topic>Synchronization</topic><topic>Variation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Stefano Filho, Carlos A</creatorcontrib><creatorcontrib>Attux, Romis</creatorcontrib><creatorcontrib>Castellano, Gabriela</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Science Database (Alumni Edition)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Biological Sciences</collection><collection>ProQuest Science Journals</collection><collection>Biological Science Database</collection><collection>ProQuest - Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ: Directory of Open Access Journals</collection><jtitle>PeerJ (San Francisco, CA)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Stefano Filho, Carlos A</au><au>Attux, Romis</au><au>Castellano, Gabriela</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EEG sensorimotor rhythms' variation and functional connectivity measures during motor imagery: linear relations and classification approaches</atitle><jtitle>PeerJ (San Francisco, CA)</jtitle><addtitle>PeerJ</addtitle><date>2017-11-08</date><risdate>2017</risdate><volume>5</volume><spage>e3983</spage><epage>e3983</epage><pages>e3983-e3983</pages><artnum>e3983</artnum><issn>2167-8359</issn><eissn>2167-8359</eissn><abstract>Hands motor imagery (MI) has been reported to alter synchronization patterns amongst neurons, yielding variations in the mu and beta bands' power spectral density (PSD) of the electroencephalography (EEG) signal. These alterations have been used in the field of brain-computer interfaces (BCI), in an attempt to assign distinct MI tasks to commands of such a system. Recent studies have highlighted that information may be missing if knowledge about brain functional connectivity is not considered. In this work, we modeled the brain as a graph in which each EEG electrode represents a node. Our goal was to understand if there exists any linear correlation between variations in the synchronization patterns-that is, variations in the PSD of mu and beta bands-induced by MI and alterations in the corresponding functional networks. Moreover, we (1) explored the feasibility of using functional connectivity parameters as features for a classifier in the context of an MI-BCI; (2) investigated three different types of feature selection (FS) techniques; and (3) compared our approach to a more traditional method using the signal PSD as classifier inputs. Ten healthy subjects participated in this study. We observed significant correlations (
< 0.05) with values ranging from 0.4 to 0.9 between PSD variations and functional network alterations for some electrodes, prominently in the beta band. The PSD method performed better for data classification, with mean accuracies of (90 ± 8)% and (87 ± 7)% for the mu and beta band, respectively, versus (83 ± 8)% and (83 ± 7)% for the same bands for the graph method. Moreover, the number of features for the graph method was considerably larger. However, results for both methods were relatively close, and even overlapped when the uncertainties of the accuracy rates were considered. Further investigation regarding a careful exploration of other graph metrics may provide better alternatives.</abstract><cop>United States</cop><pub>PeerJ. Ltd</pub><pmid>29134143</pmid><doi>10.7717/peerj.3983</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2167-8359 |
| ispartof | PeerJ (San Francisco, CA), 2017-11, Vol.5, p.e3983-e3983, Article e3983 |
| issn | 2167-8359 2167-8359 |
| language | eng |
| recordid | cdi_doaj_primary_oai_doaj_org_article_39dadb127be54bd580284f9364dbad19 |
| source | Open Access: PubMed Central; ProQuest - Publicly Available Content Database |
| subjects | Analysis BCI Biomedical engineering Brain-computer interface Classification Computational Science Computer engineering EEG Electrodes Electroencephalography Emulation Fourier transforms Hands Human-Computer Interaction Interfaces Localization (Brain function) Mental task performance Motor imagery Motor skills Neural networks Neurology Neuroscience Neurosciences Physiological aspects Rehabilitation Sensorimotor system Signal processing Spectrum analysis Studies Synchronization Variation |
| title | EEG sensorimotor rhythms' variation and functional connectivity measures during motor imagery: linear relations and classification approaches |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T13%3A21%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=EEG%20sensorimotor%20rhythms'%20variation%20and%20functional%20connectivity%20measures%20during%20motor%20imagery:%20linear%20relations%20and%20classification%20approaches&rft.jtitle=PeerJ%20(San%20Francisco,%20CA)&rft.au=Stefano%20Filho,%20Carlos%20A&rft.date=2017-11-08&rft.volume=5&rft.spage=e3983&rft.epage=e3983&rft.pages=e3983-e3983&rft.artnum=e3983&rft.issn=2167-8359&rft.eissn=2167-8359&rft_id=info:doi/10.7717/peerj.3983&rft_dat=%3Cgale_doaj_%3EA513768090%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c570t-b702e2068f8c7866e52c10ef466e9d30f00b219d0f2a081873a5c7e061dbb5793%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1961731753&rft_id=info:pmid/29134143&rft_galeid=A513768090&rfr_iscdi=true |