Analysis of Physiological Responses and Use of Fuzzy Information Granulation–Based Neural Network for Recognition of Three Emotions

摘要: In this study, we investigate the relationship between emotions and physiological responses, with emotion recognition, using proposed fuzzy information granulation-based neural network (FIGNN) for boredom, pain, surprise emotions. For an analysis of three are induced through emotional stimuli, signals obtained from evoked To recognize emotions, design FIGNN recognizer deal feature selection signals. The method is accomplished in premise, consequence, aggregation phases. premise phase takes granulation c-means clustering, consequence adopts a polynomial function, resorts to general inference. Experiments show that suitable methodology substantial reduction space can be accomplished, has high recognition accuracy