Emotion Recognition for hHman-Machine Communication
- 1 September 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530858,p. 1210-1215
Abstract
The ability to recognize emotion is one of the hallmarks of emotion intelligence. This paper proposed to recognize emotion using physiological signals obtained from multiple subjects. IAPS images were used to elicit target emotions. Five physiological signals: Blood volume pulse (BVP), Electromyography (EMG), Skin Conductance (SC), Skin Temperature (SKT) and Respiration (RESP) were selected to extract 30 features for recognition. Two pattern classification methods, Fisher discriminant and SVM method are used and compared for emotional state classification. The experimental results indicate that the proposed method provides very stable and successful emotional classification performance as 92% over six emotional states.Keywords
This publication has 15 references indexed in Scilit:
- Emotional interaction model for a service robot2006
- From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification2005
- Using physiological measures for emotional assessment: A computer-aided tool for cognitive and behavioural therapyInternational Journal on Disability and Human Development, 2005
- Using Noninvasive Wearable Computers to Recognize Human Emotions from Physiological SignalsEURASIP Journal on Advances in Signal Processing, 2004
- Emotion recognition from physiological signals using wireless sensors for presence technologiesCognition, Technology & Work, 2004
- Digital processing of affective signals2002
- Signal processing for recognition of human frustration2002
- Emotion recognition in human-computer interactionIEEE Signal Processing Magazine, 2001
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- Electrodermal Activity1992