A three-stage decision framework for multi-subject emotion recognition using physiological signals

• Published in: 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) pp. 470 - 474
• Main Authors: Jing Chen, Bin Hu, Yue Wang, Yongqiang Dai, Yuan Yao, Shengjie Zhao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2016
• Subjects: affective computing; Brain models; Emotion recognition; Feature extraction; multimodal physiological signals; Physiology; Probability; subject-independent; Videos
• DOI: 10.1109/BIBM.2016.7822562

This paper investigates the potential of physiological signals as reliable channels for multi-subject emotion recognition. A three-stage decision framework is proposed for recognizing four emotions of multiple subjects. The decision framework consists of three stages: (1) in the initial stage, identifying a subject group that a test subject can be mapped to; (2) in the second stage, identifying an emotion pool that an instance of the test subject can be assigned to; and (3) in the final stage, generating the predicted emotion from the given emotion pool for the test instance. In comparison with a series of alternative methods, the high accuracy of 70.04% achieved by our proposed method clearly demonstrates the potential of the three-stage decision method in multi-subject emotion recognition.