Deep Physiological Affect Network for the Recognition of Human Emotions

Cited 42 time in webofscience Cited 43 time in scopus
  • Hit : 286
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Byung Hyungko
dc.contributor.authorJo, Sunghoko
dc.date.accessioned2020-07-18T00:57:45Z-
dc.date.available2020-07-18T00:57:45Z-
dc.date.created2018-01-27-
dc.date.created2018-01-27-
dc.date.issued2020-04-
dc.identifier.citationIEEE TRANSACTIONS ON AFFECTIVE COMPUTING, v.11, no.2, pp.230 - 243-
dc.identifier.issn1949-3045-
dc.identifier.urihttp://hdl.handle.net/10203/275515-
dc.description.abstractHere we present a robust physiological model for the recognition of human emotions, called Deep Physiological Affect Network. This model is based on a convolutional long short-term memory (ConvLSTM) network and a new temporal margin-based loss function. Formulating the emotion recognition problem as a spectral-temporal sequence classification problem of bipolar EEG signals underlying brain lateralization and photoplethysmogram signals, the proposed model improves the performance of emotion recognition. Specifically, the new loss function allows the model to be more confident as it observes more of specific feelings while training ConvLSTM models. The function is designed to result in penalties for the violation of such confidence. Our experiments on a public dataset show that our deep physiological learning technology significantly increases the recognition rate of state-of-the-art techniques by 15.96% increase in accuracy. An extensive analysis of the relationship between participants' emotion ratings and physiological changes in brain lateralization function during the experiment is also presented.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.titleDeep Physiological Affect Network for the Recognition of Human Emotions-
dc.typeArticle-
dc.identifier.wosid000542957100004-
dc.identifier.scopusid2-s2.0-85040549078-
dc.type.rimsART-
dc.citation.volume11-
dc.citation.issue2-
dc.citation.beginningpage230-
dc.citation.endingpage243-
dc.citation.publicationnameIEEE TRANSACTIONS ON AFFECTIVE COMPUTING-
dc.identifier.doi10.1109/TAFFC.2018.2790939-
dc.contributor.localauthorJo, Sungho-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorEmotion recognition-
dc.subject.keywordAuthorPhysiology-
dc.subject.keywordAuthorBrain modeling-
dc.subject.keywordAuthorElectroencephalography-
dc.subject.keywordAuthorBiomedical monitoring-
dc.subject.keywordAuthorConvolution-
dc.subject.keywordAuthorSensors-
dc.subject.keywordAuthorEmotion recognition-
dc.subject.keywordAuthoraffective computing-
dc.subject.keywordAuthorphysiological signals-
dc.subject.keywordAuthorEEG-
dc.subject.keywordAuthorPPG-
dc.subject.keywordAuthorconvolutional-
dc.subject.keywordAuthorLSTM-
dc.subject.keywordAuthoremotional lateralization-
dc.subject.keywordAuthorinter-hemispheric asymmetry-
dc.subject.keywordAuthorvalence-
dc.subject.keywordAuthorarousal-
dc.subject.keywordPlusEEG-
dc.subject.keywordPlusCLASSIFICATION-
dc.subject.keywordPlusNEUROSCIENCE-
dc.subject.keywordPlusFRAMEWORK-
dc.subject.keywordPlusSYSTEMS-
dc.subject.keywordPlusMODEL-
dc.subject.keywordPlusSTATE-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 42 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0