Recognition of emotions induced by music videos using DT-CWPT

Author

Naser, D.S. ; Saha, Gobinda

Author_Institution

E&ECE Dept., Indian Inst. of Technol. Kharagpur, Kharagpur, India

fYear

2013

fDate

28-30 March 2013

Firstpage

53

Lastpage

57

Abstract

Viewers are attracted and attached to multimedia content due to their emotional experience associated with it. In this paper, we present an emotion recognition method of EEG signals elicited while watching music videos. The emotional features are extracted from EEG signals using dual-tree complex wavelet packet transform (DT-CWPT). The most discriminating emotional features are selected by Singular value decomposition (SVD), QR factorization with column pivoting (QRcp) and F-ratio based method. The selected features are used to train support vector machine (SVM) to classify emotion for each video using leave-one-out cross-validation strategy.

Keywords

electroencephalography; emotion recognition; medical signal processing; singular value decomposition; support vector machines; wavelet transforms; DT-CWPT; EEG signal extraction; F-ratio based method; QR factorization; SVM; column pivoting; dual-tree complex wavelet packet transform; emotion recognition method; emotional features; leave-one-out cross-validation strategy; multimedia content; music videos; singular value decomposition; support vector machine; Electroencephalography; Emotion recognition; Multimedia communication; Physiology; Videos; Wavelet packets; Dual-tree complex wavelet packet transform (DTCWPT); F-ratio and support vector machine (SVM); QR factorization with column pivoting (QRcp); electroencephalogram; singular vector decomposition (SVD);

fLanguage

English

Publisher

ieee

Conference_Titel

Medical Informatics and Telemedicine (ICMIT), 2013 Indian Conference on

Conference_Location

Kharagpur

Print_ISBN

978-1-4673-5840-8

Type

conf

DOI

10.1109/IndianCMIT.2013.6529408

Filename

6529408