An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task
As a new type of brain–computer interface (BCI), the rapid serial visual presentation (RSVP) paradigm has attracted significant attention. The mechanism of RSVP is detecting the P300 component corresponding to the target image to realize fast and correct recognition. This paper proposed an improved...
Gespeichert in:
| Veröffentlicht in: | Brain and neuroscience advances 2022-06, Vol.8 (2), p.111-126 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 126 |
|---|---|
| container_issue | 2 |
| container_start_page | 111 |
| container_title | Brain and neuroscience advances |
| container_volume | 8 |
| creator | Zhang, Hongfei Wang, Zehui Yu, Yinhu Yin, Haojun Chen, Chuangquan Wang, Hongtao |
| description | As a new type of brain–computer interface (BCI), the rapid serial visual presentation (RSVP) paradigm has attracted significant attention. The mechanism of RSVP is detecting the P300 component corresponding to the target image to realize fast and correct recognition. This paper proposed an improved EEGNet model to achieve good performance in offline and online data. Specifically, the data were filtered by xDAWN to enhance the signal-to-noise ratio of the electroencephalogram (EEG) signals. The focal loss function was used instead of the cross-entropy loss function to solve the classification problems of unbalanced samples. Additionally, the subject-specific data were fed to the improved EEGNet model to obtain a subject-specific model. We applied the proposed model at the BCI Controlled Robot Contest in World Robot Contest 2021 and won the second place. The average recall rate of the four participants reached 51.56% in triple classification. In the offline data benchmark dataset (64 subjects-RSVP tasks), the average recall rates of groups A and B reached 76.07% and 78.11%, respectively. We provided an alternative method to identify targets based on the RSVP paradigm. |
| doi_str_mv | 10.26599/BSA.2022.9050007 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2912036177</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sage_id>10.26599_BSA.2022.9050007</sage_id><sourcerecordid>2802229877</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2287-fe34951b349e923c18b92c8613cdc1e7e953b057e3040870599a10f6e8ddcbbb3</originalsourceid><addsrcrecordid>eNp9kFFLwzAQx4MoOOY-gG8Fn1svydomj3PMTRj6oD6HNL2OzK6tSTfw25utA33Rl7sj_P4X7kfILYWEZamU9w-vs4QBY4mEFADyCzJiILM4lam4_DVfk4n320AwARz4dETUrInsrnPtActosVg-Yx9VrYu8bTY1xr2zuj6-R6bW3tvKGt3bNmSayOnOlpHHE3Kwfh9a59Bj0w9Mr_3HDbmqdO1xcu5j8v64eJuv4vXL8mk-W8eGMZHHFfKpTGkRKkrGDRWFZEZklJvSUMxRpryANEcOUxA5hKM1hSpDUZamKAo-JnfD3nDK5x59r7bt3jXhS8UkZcAzmuf_UiL4Y1KcKDpQxrXeO6xU5-xOuy9FQZ2EqyBcHYWrs_CQSYaM1xv82fp34Btu239b</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2802229877</pqid></control><display><type>article</type><title>An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task</title><source>ProQuest Central Essentials</source><source>ProQuest Central (Alumni Edition)</source><source>ProQuest Central Student</source><source>Sage Journals GOLD Open Access 2024</source><source>ProQuest Central Korea</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>ProQuest Central UK/Ireland</source><source>PubMed Central</source><source>ProQuest Central</source><creator>Zhang, Hongfei ; Wang, Zehui ; Yu, Yinhu ; Yin, Haojun ; Chen, Chuangquan ; Wang, Hongtao</creator><creatorcontrib>Zhang, Hongfei ; Wang, Zehui ; Yu, Yinhu ; Yin, Haojun ; Chen, Chuangquan ; Wang, Hongtao</creatorcontrib><description>As a new type of brain–computer interface (BCI), the rapid serial visual presentation (RSVP) paradigm has attracted significant attention. The mechanism of RSVP is detecting the P300 component corresponding to the target image to realize fast and correct recognition. This paper proposed an improved EEGNet model to achieve good performance in offline and online data. Specifically, the data were filtered by xDAWN to enhance the signal-to-noise ratio of the electroencephalogram (EEG) signals. The focal loss function was used instead of the cross-entropy loss function to solve the classification problems of unbalanced samples. Additionally, the subject-specific data were fed to the improved EEGNet model to obtain a subject-specific model. We applied the proposed model at the BCI Controlled Robot Contest in World Robot Contest 2021 and won the second place. The average recall rate of the four participants reached 51.56% in triple classification. In the offline data benchmark dataset (64 subjects-RSVP tasks), the average recall rates of groups A and B reached 76.07% and 78.11%, respectively. We provided an alternative method to identify targets based on the RSVP paradigm.</description><identifier>ISSN: 2096-5958</identifier><identifier>EISSN: 2096-5958</identifier><identifier>EISSN: 2398-2128</identifier><identifier>DOI: 10.26599/BSA.2022.9050007</identifier><language>eng</language><publisher>London, England: SAGE Publications</publisher><subject>Accuracy ; Algorithms ; Classification ; Competition ; Computer peripherals ; Datasets ; Deep learning ; EEG ; Electrodes ; Electroencephalography ; Entropy ; Event-related potentials ; Machine learning ; Performance evaluation ; Robots</subject><ispartof>Brain and neuroscience advances, 2022-06, Vol.8 (2), p.111-126</ispartof><rights>The authors 2022</rights><rights>2022. This work is published under https://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>The authors 2022. This work is licensed under the Creative Commons Attribution – Non-Commercial License https://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2287-fe34951b349e923c18b92c8613cdc1e7e953b057e3040870599a10f6e8ddcbbb3</citedby><cites>FETCH-LOGICAL-c2287-fe34951b349e923c18b92c8613cdc1e7e953b057e3040870599a10f6e8ddcbbb3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2802229877/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2912036177?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,21386,21387,21388,21389,21964,23254,27851,27922,27923,33528,33701,33742,34003,34312,43657,43785,43803,43951,44065,44943,45331,64383,64387,72239,73874,74053,74072,74243,74360</link.rule.ids></links><search><creatorcontrib>Zhang, Hongfei</creatorcontrib><creatorcontrib>Wang, Zehui</creatorcontrib><creatorcontrib>Yu, Yinhu</creatorcontrib><creatorcontrib>Yin, Haojun</creatorcontrib><creatorcontrib>Chen, Chuangquan</creatorcontrib><creatorcontrib>Wang, Hongtao</creatorcontrib><title>An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task</title><title>Brain and neuroscience advances</title><description>As a new type of brain–computer interface (BCI), the rapid serial visual presentation (RSVP) paradigm has attracted significant attention. The mechanism of RSVP is detecting the P300 component corresponding to the target image to realize fast and correct recognition. This paper proposed an improved EEGNet model to achieve good performance in offline and online data. Specifically, the data were filtered by xDAWN to enhance the signal-to-noise ratio of the electroencephalogram (EEG) signals. The focal loss function was used instead of the cross-entropy loss function to solve the classification problems of unbalanced samples. Additionally, the subject-specific data were fed to the improved EEGNet model to obtain a subject-specific model. We applied the proposed model at the BCI Controlled Robot Contest in World Robot Contest 2021 and won the second place. The average recall rate of the four participants reached 51.56% in triple classification. In the offline data benchmark dataset (64 subjects-RSVP tasks), the average recall rates of groups A and B reached 76.07% and 78.11%, respectively. We provided an alternative method to identify targets based on the RSVP paradigm.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Classification</subject><subject>Competition</subject><subject>Computer peripherals</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>EEG</subject><subject>Electrodes</subject><subject>Electroencephalography</subject><subject>Entropy</subject><subject>Event-related potentials</subject><subject>Machine learning</subject><subject>Performance evaluation</subject><subject>Robots</subject><issn>2096-5958</issn><issn>2096-5958</issn><issn>2398-2128</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>AFRWT</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>AZQEC</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp9kFFLwzAQx4MoOOY-gG8Fn1svydomj3PMTRj6oD6HNL2OzK6tSTfw25utA33Rl7sj_P4X7kfILYWEZamU9w-vs4QBY4mEFADyCzJiILM4lam4_DVfk4n320AwARz4dETUrInsrnPtActosVg-Yx9VrYu8bTY1xr2zuj6-R6bW3tvKGt3bNmSayOnOlpHHE3Kwfh9a59Bj0w9Mr_3HDbmqdO1xcu5j8v64eJuv4vXL8mk-W8eGMZHHFfKpTGkRKkrGDRWFZEZklJvSUMxRpryANEcOUxA5hKM1hSpDUZamKAo-JnfD3nDK5x59r7bt3jXhS8UkZcAzmuf_UiL4Y1KcKDpQxrXeO6xU5-xOuy9FQZ2EqyBcHYWrs_CQSYaM1xv82fp34Btu239b</recordid><startdate>202206</startdate><enddate>202206</enddate><creator>Zhang, Hongfei</creator><creator>Wang, Zehui</creator><creator>Yu, Yinhu</creator><creator>Yin, Haojun</creator><creator>Chen, Chuangquan</creator><creator>Wang, Hongtao</creator><general>SAGE Publications</general><general>Sage Publications Ltd</general><scope>AFRWT</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7TK</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PSYQQ</scope><scope>7RV</scope><scope>88G</scope><scope>AZQEC</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>KB0</scope><scope>M2M</scope><scope>NAPCQ</scope><scope>PIMPY</scope><scope>Q9U</scope></search><sort><creationdate>202206</creationdate><title>An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task</title><author>Zhang, Hongfei ; Wang, Zehui ; Yu, Yinhu ; Yin, Haojun ; Chen, Chuangquan ; Wang, Hongtao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2287-fe34951b349e923c18b92c8613cdc1e7e953b057e3040870599a10f6e8ddcbbb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Classification</topic><topic>Competition</topic><topic>Computer peripherals</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>EEG</topic><topic>Electrodes</topic><topic>Electroencephalography</topic><topic>Entropy</topic><topic>Event-related potentials</topic><topic>Machine learning</topic><topic>Performance evaluation</topic><topic>Robots</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Hongfei</creatorcontrib><creatorcontrib>Wang, Zehui</creatorcontrib><creatorcontrib>Yu, Yinhu</creatorcontrib><creatorcontrib>Yin, Haojun</creatorcontrib><creatorcontrib>Chen, Chuangquan</creatorcontrib><creatorcontrib>Wang, Hongtao</creatorcontrib><collection>Sage Journals GOLD Open Access 2024</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Neurosciences Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical 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 One Psychology</collection><collection>Nursing & Allied Health Database</collection><collection>Psychology Database (Alumni)</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>Psychology Database</collection><collection>Nursing & Allied Health Premium</collection><collection>Publicly Available Content Database</collection><collection>ProQuest Central Basic</collection><jtitle>Brain and neuroscience advances</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Hongfei</au><au>Wang, Zehui</au><au>Yu, Yinhu</au><au>Yin, Haojun</au><au>Chen, Chuangquan</au><au>Wang, Hongtao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task</atitle><jtitle>Brain and neuroscience advances</jtitle><date>2022-06</date><risdate>2022</risdate><volume>8</volume><issue>2</issue><spage>111</spage><epage>126</epage><pages>111-126</pages><issn>2096-5958</issn><eissn>2096-5958</eissn><eissn>2398-2128</eissn><abstract>As a new type of brain–computer interface (BCI), the rapid serial visual presentation (RSVP) paradigm has attracted significant attention. The mechanism of RSVP is detecting the P300 component corresponding to the target image to realize fast and correct recognition. This paper proposed an improved EEGNet model to achieve good performance in offline and online data. Specifically, the data were filtered by xDAWN to enhance the signal-to-noise ratio of the electroencephalogram (EEG) signals. The focal loss function was used instead of the cross-entropy loss function to solve the classification problems of unbalanced samples. Additionally, the subject-specific data were fed to the improved EEGNet model to obtain a subject-specific model. We applied the proposed model at the BCI Controlled Robot Contest in World Robot Contest 2021 and won the second place. The average recall rate of the four participants reached 51.56% in triple classification. In the offline data benchmark dataset (64 subjects-RSVP tasks), the average recall rates of groups A and B reached 76.07% and 78.11%, respectively. We provided an alternative method to identify targets based on the RSVP paradigm.</abstract><cop>London, England</cop><pub>SAGE Publications</pub><doi>10.26599/BSA.2022.9050007</doi><tpages>16</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2096-5958 |
| ispartof | Brain and neuroscience advances, 2022-06, Vol.8 (2), p.111-126 |
| issn | 2096-5958 2096-5958 2398-2128 |
| language | eng |
| recordid | cdi_proquest_journals_2912036177 |
| source | ProQuest Central Essentials; ProQuest Central (Alumni Edition); ProQuest Central Student; Sage Journals GOLD Open Access 2024; ProQuest Central Korea; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; ProQuest Central UK/Ireland; PubMed Central; ProQuest Central |
| subjects | Accuracy Algorithms Classification Competition Computer peripherals Datasets Deep learning EEG Electrodes Electroencephalography Entropy Event-related potentials Machine learning Performance evaluation Robots |
| title | An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T07%3A55%3A07IST&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=An%20improved%20EEGNet%20for%20single-trial%20EEG%20classification%20in%20rapid%20serial%20visual%20presentation%20task&rft.jtitle=Brain%20and%20neuroscience%20advances&rft.au=Zhang,%20Hongfei&rft.date=2022-06&rft.volume=8&rft.issue=2&rft.spage=111&rft.epage=126&rft.pages=111-126&rft.issn=2096-5958&rft.eissn=2096-5958&rft_id=info:doi/10.26599/BSA.2022.9050007&rft_dat=%3Cproquest_cross%3E2802229877%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2802229877&rft_id=info:pmid/&rft_sage_id=10.26599_BSA.2022.9050007&rfr_iscdi=true |