Logo image
Back
Biometric valence and arousal recognition
Conference paper   Peer reviewed

Biometric valence and arousal recognition

Christian M Jones and T Troen
Proceedings of OZCHI 2007, pp.191-194
OZCHI: Conference of the Australian Computer-Human Interaction Special Interest Group (CHISIG) of the Human Factors and Ergonomics Society of Australia (HFESA): Entertaining user interfaces, 2007 (Adelaide, Australia, 29-Nov-2007–30-Nov-2007)
Association for Computer Machinery
2007
DOI: https://doi.org/10.1145/1324892.1324929
url
https://doi.org/10.1145/1324892.1324929View
Published Version

Abstract

affective computing biometrics emotion recognition valence and arousal
A real-time user-independent emotion detection system using physiological signals has been developed. The system has the ability to classify affective states into 2-dimensions using valence and arousal. Each dimension ranges from 1 to 5 giving a total of 25 possible affective regions. Physiological signals were measured using 3 biometric sensors for Blood Volume Pulse (BVP), Skin Conductance (SC) and Respiration (RESP). Two emotion inducing experiments were conducted to acquire physiological data from 13 subjects. The data from 10 of these subjects were used to train the system, while the remaining 3 datasets were used to test the performance of the system. A recognition rate of 62% for valence and 67% for arousal was achieved within +/- 1 units of the valence and arousal rating.

Details

Metrics

1 File views/ downloads
903 Record Views
Logo image