BROWSE
Detail
Conference Paper
The Design of Fuzzy C-Means Clustering Based Neural Networks for Emotion Classification
Cited 4 time in 
Share 
Share
- Authors
- B.-J. Park, E.-H. Jang, S.-H. Kim, C. Huh, M.-A. Chung
- Issue Date
- 2013-06
- Citation
- Joint International Fuzzy Systems Association World Congress and North American Fuzzy Information Processing Society Annual Meeting (IFSA/NAFIPS) 2013, pp.413-417
- Language
- English
- Type
- Conference Paper
- Abstract
- In this study, we investigate the use of a Fuzzy C-Means Clustering based Neural Network (FNN) classifier in problems of emotion classification. The proposed classifier model consists of three layers, namely, input, hidden and output layers. Here, fuzzy c-means clustering method, two types of polynomial and linear combination function are used as a kernel function in the input layer, the hidden layer and the output layer of networks, respectively. From the conceptual standpoint, the classifier of this form is constructed by employing two development mechanisms. Fuzzy clustering (Fuzzy C-Means, FCM) is aimed at the development of input layer of the networks while the corresponding neurons of the networks are formed by some local polynomials. The purpose of this study is to classify the emotions using physiological signals induced by three different emotions (boredom, pain and surprise). Three different emotional states are evoked by emotional stimuli, physiological signals (EDA, ECG, PPG and SKT) for the induced emotions are measured as the reactions of stimuli, and 27 features are extracted from their physiological signals for emotion classification using the proposed FNN classifier. To evaluate the performance of emotion classification of the proposed model, we use the 10-fold cross validation and a comparative analysis shows that the proposed model exhibit higher accuracy when compared with some other models that exist in the literature. © 2013 IEEE.
- KSP Keywords
- Classifier model, Comparative analysis, Cross validation(CV), Emotional states, Fuzzy Clustering, Fuzzy c-means clustering method, Input layer, Output layer, Physiological signals, Proposed model, clustering based