EEG-based emotion recognition using wavelet features

Author

Zhengjie Zhou ; Huiping Jiang ; Xiaoyuan Song

Author_Institution

MinZu Univ. of China, Beijing, China

fYear

2014

fDate

27-29 June 2014

Firstpage

585

Lastpage

588

Abstract

This paper described a research project conducted to recognize to finding the relationship between EEG signals and Human emotions. EEG signals are used to classify three kinds of emotions, positive, neuter and negative. Firstly, literature research has been performed to establish a suitable approach for emotion recognition. Secondly, we extracted features from original EEG data using 4-order wavelet and put them in SVM classifier with different kernel functions. The result shows that an SVM with linear kernel has higher average test accuracy than other kernel function.

Keywords

electroencephalography; feature extraction; medical computing; support vector machines; 4-order wavelet; EEG data; EEG signals; EEG-based emotion recognition; SVM classifier; feature extraction; human emotions; kernel functions; wavelet features; Accuracy; Electroencephalography; Emotion recognition; Feature extraction; Kernel; Speech recognition; Support vector machines; Brain-computer interaction; electroencephalogram; emotion recognition; wavelet;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering and Service Science (ICSESS), 2014 5th IEEE International Conference on

Conference_Location

Beijing

ISSN

2327-0586

Print_ISBN

978-1-4799-3278-8

Type

conf

DOI

10.1109/ICSESS.2014.6933636

Filename

6933636