Integration of affective computing techniques and soft computing for developing a human affective recognition system for U-learning systems
by Chih-Hung Wu; Yi-Lin Tzeng; Bor-Chen Kuo; Gwo-Hshiung Tzeng
International Journal of Mobile Learning and Organisation (IJMLO), Vol. 8, No. 1, 2014

Abstract: In this study, a human affective norm (emotion and attention) recognition system for U-learning systems is developed. Fifth graders in an elementary school were recruited as participants firstly to see some emotional pictures from the International Affective Picture System (IAPS), and to do the attention test to obtain the affective information - electroencephalography (EEG) and electrocardiogram (ECG) for developing the affective norm recognition system of the study. These bio-physiology signals extract important features by using four types of linear Principal Component Analysis (PCA) to serve as the input variables for Support Vector Machine (SVM) model. The results of feature selection showed that factor analysis with covariance extraction method has higher accumulative variances than correlation extraction method. This study suggested that future researchers may try to adopt more non-linear feature selection methods in order to develop a high accuracy SVM-based emotion recognition system.

Online publication date: Wed, 22-Oct-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Mobile Learning and Organisation (IJMLO):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com