Home // COGNITIVE 2014, The Sixth International Conference on Advanced Cognitive Technologies and Applications // View article

A Design of Memory-based Learning Classifier usign Genteic Strategy for Emotion Classification

Authors:
Byoung-Jun Park
Eun-Hye Jang
Sang-Hyeob Kim
Chul Huh
Myung-Ae Chung

Keywords: memory-based learning; emotion classification; pysiological signals; genetic algorithms

Abstract:
In this study, we discuss emotion classification for seven kinds of emotion (happiness, sadness, anger, fear, disgust, surprise, stress) in the psycho-physiological research. Seven emotions are evoked by stimulus formed on audio-visual film clips, and then physiological signals of autonomic nervous system responses are measured for the reaction of stimulation. Additionally, seven different emotions will be classified by the proposed classification methodology using physiological signals. We introduce a classification methodology on memory-based learning that dwells upon the usage of genetic strategy (Genetic Algorithms). Genetic algorithms (GAs) take selection problems of instances and features of memory into two level optimization processes. In the first level, GAs chooses P % of instances as a set of memory comes from instances with c classes. In the second level of the optimization process, GAs is instrumental in the formation of a core set of features that is a collection of the most meaningful and discriminative components of the original feature space. In classification problems, it becomes important to carefully select instances and establish a subset of features in order to achieve a sound performance of a classifier. The study offers a complete algorithmic framework and demonstrates the effectiveness of the approach for the classification of seven emotions. Numerical experiments show that a suitable selection of instances and a substantial reduction of the feature space could be accomplished and the classifier formed in this manner is characterized by high classification accuracy for the seven emotions based on physiological signals.

Pages: 120 to 125

Copyright: Copyright (c) IARIA, 2014

Publication date: May 25, 2014

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-340-7

Location: Venice, Italy

Dates: from May 25, 2014 to May 29, 2014