Affective computing
Toward Machine Emotional Intelligence: Analysis of Affective Physiological State
IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
ISWC '97 Proceedings of the 1st IEEE International Symposium on Wearable Computers
Using noninvasive wearable computers to recognize human emotions from physiological signals
EURASIP Journal on Applied Signal Processing
Neural network based emotion estimation using heart rate variability and skin resistance
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Hi-index | 0.00 |
For the Ubiquitous computing system, a well designed computer interface should have the ability of making the user feel comfortable so as to encourage user performance. In order to do this, systems should be able to identify the emotional state of the user. Thus, the identification of the user's emotional state is of importance in developing context-related devices, which offer the optimal feedback to the user depending on the user's emotional state. Those devices require portability and continuous measurement for daily use, which is particularly essential for an ubiquitous healthcare device. In this paper, the portable device for bi-emotional state identification was designed using heart rate variability (HRV) extracted from beat-to-beat photoplethysmography (PPG) waveforms. A portable wrist-band type PPG measuring device was equipped with a Bluetooth communication interface to provide mobility. HRV was estimated from smoothed differentiated PPG waveforms by the absolute value of the successive beat-to-beat interval difference. Two emotional states are artificially induced by a composed video clip, and then validated by the self-assessment Manikin method. The designed device was then applied to a respiration training device to adjust the balance level of the autonomous nervous system throughout the respiration pager, whose level changes in proportion to the estimated ratio between negative and positive emotional states. Experimentation using 19 male and six female participants demonstrated the feasibility of a ubiquitous emotional feedback control device.