Integration of affective computing techniques and soft computing for developing a human affective recognition system for U-learning systems

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.