Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach

The identification of emotions is an open research area and has a potential leading role in the improvement of socio-emotional skills such as empathy, sensitivity, and emotion recognition in humans. The current study aimed at using Event Related Potential (ERP) components (N100, N200, P200, P300, ea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ACM transactions on applied perception 2024-07, Vol.21 (3), p.1-18, Article 11
Hauptverfasser: Tülay, Emine Elif, Balli, Tugçe
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 18
container_issue 3
container_start_page 1
container_title ACM transactions on applied perception
container_volume 21
creator Tülay, Emine Elif
Balli, Tugçe
description The identification of emotions is an open research area and has a potential leading role in the improvement of socio-emotional skills such as empathy, sensitivity, and emotion recognition in humans. The current study aimed at using Event Related Potential (ERP) components (N100, N200, P200, P300, early Late Positive Potential (LPP), middle LPP, and late LPP) of EEG data for the classification of emotional states (positive, negative, neutral). EEG data were collected from 62 healthy individuals over 18 electrodes. An emotional paradigm with pictures from the International Affective Picture System (IAPS) was used to record the EEG data. A linear Support Vector Machine (C = 0.1) was used to classify emotions, and a forward feature selection approach was used to eliminate irrelevant features. The early LPP component, which was the most discriminative among all ERP components, had the highest classification accuracy (70.16%) for identifying negative and neutral stimuli. The classification of negative versus neutral stimuli had the best accuracy (79.84%) when all ERP components were used as a combined feature set, followed by positive versus negative stimuli (75.00%) and positive versus neutral stimuli (68.55%). Overall, the combined ERP component feature sets outperformed single ERP component feature sets for all stimulus pairings in terms of accuracy. These findings are promising for further research and development of EEG-based emotion recognition systems.
doi_str_mv 10.1145/3657638
format Article
fullrecord <record><control><sourceid>acm_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1145_3657638</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3657638</sourcerecordid><originalsourceid>FETCH-LOGICAL-a169t-18ae4fc7613d03c82f1877fe4aea123369364514a0e239af2b7165d3938d147b3</originalsourceid><addsrcrecordid>eNo9kLtPwzAYxC0EEqUgdiZvTIF88StmC30AUhASjzn66tglqLEjpwz970nUlulOdz_dcIRcQ3oHwMU9k0JJlp-QCQjOE6alOD16IfJzctH3P2macS3EhHzMrQl149d0-evNtgkeN_QxYuPpHLdIXYh00YaxoO8DuvbN6B9oQV_RfDfe0tJi9ONC0XUxDOElOXO46e3VQafka7n4nD0n5dvTy6woEwSptwnkaLkzSgKrU2byzEGulLMcLULGmNRMcgEcU5sxjS5bKZCiZprlNXC1YlNyu981MfR9tK7qYtNi3FWQVuMX1eGLgbzZk2jaf-hY_gF_zlfD</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach</title><source>ACM Digital Library Complete</source><creator>Tülay, Emine Elif ; Balli, Tugçe</creator><creatorcontrib>Tülay, Emine Elif ; Balli, Tugçe</creatorcontrib><description>The identification of emotions is an open research area and has a potential leading role in the improvement of socio-emotional skills such as empathy, sensitivity, and emotion recognition in humans. The current study aimed at using Event Related Potential (ERP) components (N100, N200, P200, P300, early Late Positive Potential (LPP), middle LPP, and late LPP) of EEG data for the classification of emotional states (positive, negative, neutral). EEG data were collected from 62 healthy individuals over 18 electrodes. An emotional paradigm with pictures from the International Affective Picture System (IAPS) was used to record the EEG data. A linear Support Vector Machine (C = 0.1) was used to classify emotions, and a forward feature selection approach was used to eliminate irrelevant features. The early LPP component, which was the most discriminative among all ERP components, had the highest classification accuracy (70.16%) for identifying negative and neutral stimuli. The classification of negative versus neutral stimuli had the best accuracy (79.84%) when all ERP components were used as a combined feature set, followed by positive versus negative stimuli (75.00%) and positive versus neutral stimuli (68.55%). Overall, the combined ERP component feature sets outperformed single ERP component feature sets for all stimulus pairings in terms of accuracy. These findings are promising for further research and development of EEG-based emotion recognition systems.</description><identifier>ISSN: 1544-3558</identifier><identifier>EISSN: 1544-3965</identifier><identifier>DOI: 10.1145/3657638</identifier><language>eng</language><publisher>New York, NY: ACM</publisher><subject>Computing methodologies ; Cross-validation ; Feature selection ; Supervised learning by classification</subject><ispartof>ACM transactions on applied perception, 2024-07, Vol.21 (3), p.1-18, Article 11</ispartof><rights>Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-a169t-18ae4fc7613d03c82f1877fe4aea123369364514a0e239af2b7165d3938d147b3</cites><orcidid>0000-0002-6509-3725 ; 0000-0003-0150-5476</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://dl.acm.org/doi/pdf/10.1145/3657638$$EPDF$$P50$$Gacm$$Hfree_for_read</linktopdf><link.rule.ids>314,776,780,2276,27901,27902,40172,75971</link.rule.ids></links><search><creatorcontrib>Tülay, Emine Elif</creatorcontrib><creatorcontrib>Balli, Tugçe</creatorcontrib><title>Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach</title><title>ACM transactions on applied perception</title><addtitle>ACM TAP</addtitle><description>The identification of emotions is an open research area and has a potential leading role in the improvement of socio-emotional skills such as empathy, sensitivity, and emotion recognition in humans. The current study aimed at using Event Related Potential (ERP) components (N100, N200, P200, P300, early Late Positive Potential (LPP), middle LPP, and late LPP) of EEG data for the classification of emotional states (positive, negative, neutral). EEG data were collected from 62 healthy individuals over 18 electrodes. An emotional paradigm with pictures from the International Affective Picture System (IAPS) was used to record the EEG data. A linear Support Vector Machine (C = 0.1) was used to classify emotions, and a forward feature selection approach was used to eliminate irrelevant features. The early LPP component, which was the most discriminative among all ERP components, had the highest classification accuracy (70.16%) for identifying negative and neutral stimuli. The classification of negative versus neutral stimuli had the best accuracy (79.84%) when all ERP components were used as a combined feature set, followed by positive versus negative stimuli (75.00%) and positive versus neutral stimuli (68.55%). Overall, the combined ERP component feature sets outperformed single ERP component feature sets for all stimulus pairings in terms of accuracy. These findings are promising for further research and development of EEG-based emotion recognition systems.</description><subject>Computing methodologies</subject><subject>Cross-validation</subject><subject>Feature selection</subject><subject>Supervised learning by classification</subject><issn>1544-3558</issn><issn>1544-3965</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNo9kLtPwzAYxC0EEqUgdiZvTIF88StmC30AUhASjzn66tglqLEjpwz970nUlulOdz_dcIRcQ3oHwMU9k0JJlp-QCQjOE6alOD16IfJzctH3P2macS3EhHzMrQl149d0-evNtgkeN_QxYuPpHLdIXYh00YaxoO8DuvbN6B9oQV_RfDfe0tJi9ONC0XUxDOElOXO46e3VQafka7n4nD0n5dvTy6woEwSptwnkaLkzSgKrU2byzEGulLMcLULGmNRMcgEcU5sxjS5bKZCiZprlNXC1YlNyu981MfR9tK7qYtNi3FWQVuMX1eGLgbzZk2jaf-hY_gF_zlfD</recordid><startdate>20240731</startdate><enddate>20240731</enddate><creator>Tülay, Emine Elif</creator><creator>Balli, Tugçe</creator><general>ACM</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-6509-3725</orcidid><orcidid>https://orcid.org/0000-0003-0150-5476</orcidid></search><sort><creationdate>20240731</creationdate><title>Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach</title><author>Tülay, Emine Elif ; Balli, Tugçe</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a169t-18ae4fc7613d03c82f1877fe4aea123369364514a0e239af2b7165d3938d147b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computing methodologies</topic><topic>Cross-validation</topic><topic>Feature selection</topic><topic>Supervised learning by classification</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tülay, Emine Elif</creatorcontrib><creatorcontrib>Balli, Tugçe</creatorcontrib><collection>CrossRef</collection><jtitle>ACM transactions on applied perception</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tülay, Emine Elif</au><au>Balli, Tugçe</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach</atitle><jtitle>ACM transactions on applied perception</jtitle><stitle>ACM TAP</stitle><date>2024-07-31</date><risdate>2024</risdate><volume>21</volume><issue>3</issue><spage>1</spage><epage>18</epage><pages>1-18</pages><artnum>11</artnum><issn>1544-3558</issn><eissn>1544-3965</eissn><abstract>The identification of emotions is an open research area and has a potential leading role in the improvement of socio-emotional skills such as empathy, sensitivity, and emotion recognition in humans. The current study aimed at using Event Related Potential (ERP) components (N100, N200, P200, P300, early Late Positive Potential (LPP), middle LPP, and late LPP) of EEG data for the classification of emotional states (positive, negative, neutral). EEG data were collected from 62 healthy individuals over 18 electrodes. An emotional paradigm with pictures from the International Affective Picture System (IAPS) was used to record the EEG data. A linear Support Vector Machine (C = 0.1) was used to classify emotions, and a forward feature selection approach was used to eliminate irrelevant features. The early LPP component, which was the most discriminative among all ERP components, had the highest classification accuracy (70.16%) for identifying negative and neutral stimuli. The classification of negative versus neutral stimuli had the best accuracy (79.84%) when all ERP components were used as a combined feature set, followed by positive versus negative stimuli (75.00%) and positive versus neutral stimuli (68.55%). Overall, the combined ERP component feature sets outperformed single ERP component feature sets for all stimulus pairings in terms of accuracy. These findings are promising for further research and development of EEG-based emotion recognition systems.</abstract><cop>New York, NY</cop><pub>ACM</pub><doi>10.1145/3657638</doi><tpages>18</tpages><orcidid>https://orcid.org/0000-0002-6509-3725</orcidid><orcidid>https://orcid.org/0000-0003-0150-5476</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1544-3558
ispartof ACM transactions on applied perception, 2024-07, Vol.21 (3), p.1-18, Article 11
issn 1544-3558
1544-3965
language eng
recordid cdi_crossref_primary_10_1145_3657638
source ACM Digital Library Complete
subjects Computing methodologies
Cross-validation
Feature selection
Supervised learning by classification
title Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T09%3A21%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-acm_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Decoding%20Functional%20Brain%20Data%20for%20Emotion%20Recognition:%20A%20Machine%20Learning%20Approach&rft.jtitle=ACM%20transactions%20on%20applied%20perception&rft.au=T%C3%BClay,%20Emine%20Elif&rft.date=2024-07-31&rft.volume=21&rft.issue=3&rft.spage=1&rft.epage=18&rft.pages=1-18&rft.artnum=11&rft.issn=1544-3558&rft.eissn=1544-3965&rft_id=info:doi/10.1145/3657638&rft_dat=%3Cacm_cross%3E3657638%3C/acm_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true