BROWSE
Detail
Conference Paper
Emotion Classification by Machine Learning Algorithm using Physiological Signals
Cited - time in 
Share 
Share
- Authors
- Eun-Hye Jang, Byoung-Jun Park, Sang-Hyeob Kim, Jin-Hun Sohn
- Issue Date
- 2012-03
- Citation
- International Conference on Machine Learning and Computing (ICMLC) 2012, pp.1-5
- Language
- English
- Type
- Conference Paper
- Abstract
- Recently, emotion studies have suggested emotion classification using machine learining algorithms based on physiological features. We classified three emotion (boredom, pain, and surprise) by 4 machine learning algorithms (LDA, CART, SOM, and SVM). 200 college students participated in this experiment. EDA, ECG, PPG, and SKT as physiological signals were acquired for 1 minute before emotional state as baseline and for 1-1.5 minutes during emotional state. 23 features were extracted from physiological signals. For emotion classification, the difference values of each feature substracting baseline from the emotional state were used for machine learning algorithms. The result showed that an accuracy of emotion classification by SVM was highest. This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals and it can be applied on human-computer interaction system for emotion detection.
- KSP Keywords
- College students, Emotion Recognition, Emotional states, Human computer interaction, Human emotions, Interaction System, Machine Learning Algorithms, Physiological features, Physiological signals, emotion classification, emotion detection