Application of J48 Decision Tree Classifier in Emotion Recognition Based on Chaos Characteristics

DOI

10.2991/amcce-15.2015.330How to use a DOI?

Keywords

multiple physiological signals; emotion recognition; chaos; decision tree

Abstract

Physiological signals are external manifestations of emotions. Mood swings can be expressed by the change of physiological signals. Because these performances are not controlled by the individual subjective consciousness, the conclusions are more objective and true. The method based on the statistical characteristics is very difficult to describe the complex changes in physiological signals, so the J48 decision tree was adopted to train and recognize the chaotic characteristics of physiological signals in the paper, which have many advantages in solving the multi-class classification problem, such as high accuracy, fast classification speed and simple classification rules. The chaos characteristic matrixes consist of the extracted chaotic characteristic parameters, which is combined J48 decision tree classifier to recognize four different emotions. The results showed emotion recognition of physiological signals based on chaotic theory is feasible.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Chun yan Nie
AU  - Ju Wang
AU  - Fang He
AU  - Reika Sato
PY  - 2015/04
DA  - 2015/04
TI  - Application of J48 Decision Tree Classifier in Emotion Recognition Based on Chaos Characteristics
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.330
DO  - 10.2991/amcce-15.2015.330
ID  - Nie2015/04
ER  -