BROWSE
Detail
Journal Article
Emotion Recognition based on ANS Responses Evoked by Negative Emotion
Cited - time in 
Share 
Share
- Authors
- Eun-Hye Jang, Byoung-Jun Park, Sang-Hyeob Kim, Yeongji Eum, Jin-Hun Sohn
- Issue Date
- 2012-03
- Citation
- International Journal of Engineering and Industries, v.3, no.1, pp.79-85
- ISSN
- 2093-5765
- Publisher
- 차세대융합기술연구원(AICIT)
- Language
- English
- Type
- Journal Article
- Abstract
- Emotion recognition is one of the core processes to implement emotional intelligence in humancomputer interaction (HCI) research. The purposes of this study were to investigate emotion-specific ANS responses and to test recognizing rate using classification algorithm based on ANS responses evoked by negative emotions such as fear, surprise, and stress. The results of one-way ANOVA toward each parameter showed that there were significant differences in NSCR, mean SCR, mean SKT, max SKT, and FFT ap_HF. Linear discriminant analysis (LDA) was tested to confirm classification rate on three emotions. In consequence, 57.3% of originally grouped cases were correctly classified. The result of this study is the basis for the emotion recognition technique in HCI as well as contributes to the standardization in emotion-specific ANS responses.
- KSP Keywords
- Classification algorithm, Classification rate, Emotion Recognition, Emotional intelligence, Human computer interaction, Negative emotions, One-way ANOVA, linear discriminant analysis(LDA), recognition technique