Emotion primitives estimation from EEG signals using Hilbert Huang Transform

Basit Öğe Kaydı
dc.authorscopusid55293603700
dc.authorscopusid7006442384
dc.authorscopusid43262125900
dc.contributor.authorUzun, S. Sinem
dc.contributor.authorYildirim, Serdar
dc.contributor.authorYildirim, Esen
dc.date.accessioned2024-09-19T15:41:18Z
dc.date.available2024-09-19T15:41:18Z
dc.date.issued2012
dc.departmentHatay Mustafa Kemal Üniversitesien_US
dc.descriptionIEEE Engineering in Medicine and Biology Society (IEEE-EMBS); Key Lab. Health Informatics, Chin. Acad. Sci. (HI-CAS); CAS-SIAT Institute of Biomedical and Health Engineering (IBHE)en_US
dc.descriptionIEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2012. In Conj. with the 8th Int. Symp.on Medical Devices and Biosensors and the 7th Int. Symp. on Biomedical and Health Engineering -- 2 January 2012 through 7 January 2012 -- Hong Kong and Shenzhen -- 91242en_US
dc.description.abstractThis paper addresses the problem of emotion primitives estimation using information obtained from EEG signals. The EEG data were collected from 18 subjects, 9 male and 9 female, aged from 19 to 26 years old. We used audio clips from International Affective Digital Sounds (IADS) as stimuli for emotion elicitation. Hilbert-Huang Transform, a proper method for non-linear and non-stationary signal processing, was used for feature extraction. EEG signals were first decomposed into their Intrinsic Mode Functions (IMFs). Then 990 features were computed from the first five IMFs. To identify the most salient features and eliminate the redundant and irrelevant ones, we performed correlation based feature selection (CFS). This feature selection process reduced the number of features dramatically while increasing the performance remarkably. In this work, we used support vector regression for estimation of each emotion primitive value. Regression mean absolute error values and their standard deviations over all subjects for valence, activation, and dominance were obtained as 1.11 (0.13), 0.65 (0.09) and 0.38 (0.06) respectively. © 2012 IEEE.en_US
dc.identifier.doi10.1109/BHI.2012.6211551
dc.identifier.endpage227en_US
dc.identifier.isbn978-145772177-9
dc.identifier.scopus2-s2.0-84864245892en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage224en_US
dc.identifier.urihttps://doi.org/10.1109/BHI.2012.6211551
dc.identifier.urihttps://hdl.handle.net/20.500.12483/14168
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.relation.ispartofProceedings - IEEE-EMBS International Conference on Biomedical and Health Informatics: Global Grand Challenge of Health Informatics, BHI 2012en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAudio acousticsen_US
dc.subjectBiomedical equipmenten_US
dc.subjectBiosensorsen_US
dc.subjectEstimationen_US
dc.subjectFeature extractionen_US
dc.subjectAudio clipsen_US
dc.subjectDigital sounden_US
dc.subjectEEG signalsen_US
dc.subjectEmotion elicitationen_US
dc.subjectHilbert Huang transformsen_US
dc.subjectIntrinsic Mode functionsen_US
dc.subjectMean absolute erroren_US
dc.subjectNonstationary signal processingen_US
dc.subjectSalient featuresen_US
dc.subjectStandard deviationen_US
dc.subjectSupport vector regression (SVR)en_US
dc.subjectSignal processingen_US
dc.titleEmotion primitives estimation from EEG signals using Hilbert Huang Transformen_US
dc.typeConference Objecten_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
[ N/A ]
İsim:
Tam Metin / Full Text
Boyut:
934.24 KB
Biçim:
Adobe Portable Document Format
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu