ECG-Based Human Emotion Recognition Across Multiple Subjects
Electrocardiogram (ECG) based affective computing is a new research field that aims to find correlates between human emotions and the registered ECG signals. Typically, emotion recognition systems are personalized, i.e. the discrimination models are subject-dependent. Building subject-independent models is a harder problem due to the high ECG variability between individuals. In this paper, we study the potential of two machine learning methods (Logistic Regression and Artificial Neural Network) to discriminate human emotional states across multiple subjects. The users were exposed to movies with different emotional content (neutral, fear, disgust) and their ECG activity was registered. Based on extracted features from the ECG recordings, the three emotional states were partially discriminated.
KeywordsECG Affective computing Human emotion recognition Machine learning Artificial Neural Networks Logistic Regression
This work was supported by European Regional Development Fund and the Operational Program “Science and Education for Smart Growth” under contract UNITe BG05M2OP001-1.001-0004-01 (2018–2023).
- 1.Konar, A., Chakraborty, A.: Emotion Recognition: A Pattern Analysis Approach. Wiley, Hoboken (2014)Google Scholar
- 2.Xu, Y.: A method of emotion recognition based on ECG signal. In: 2009 International Conference on Computational Intelligence and Natural Computing, pp. 202–205 (2009)Google Scholar
- 3.Min, H.: Analysis of affective ECG signals toward emotion I. Introduction ECG data collection III. ECG feature extraction. J. Electron. (China) 9–14 (2010)Google Scholar
- 4.Cai, J.: The research on emotion recognition from ECG signal. In: Proceedings of 2009 International Conference on Information Technology and Computer Science, ITCS 2009, pp. 497–500 (2009) Google Scholar
- 7.Selvaraj, J.: Classification of emotional states from electrocardiogram signals: a non-linear approach based on hurst. BioMed. Eng. 12, 44 (2013)Google Scholar
- 8.Keren, G.: End-to-end learning for dimensional emotion recognition from physiological signals. In: Proceedings of IEEE International Conference on Multimedia and Expo, pp. 985–990 (2017)Google Scholar