IV. TOWARDS AFFECTIVE COMPUTING

Abstract

As we have known for centuries, humans exhibit an electrical profile. This profile is altered by various psychological and physiological processes, which can be measured through biosignals (e.g., electromyography, EMG and electrodermal activity, EDA). These biosignals can reveal our emotions and, as such, can serve as an advanced man-machine interface (MMI) for emotion-aware consumer products. However, such an MMI requires the correct classification of biosignals to emotion classes. This chapter starts with a brief introduction on biosignals for emotion detection. Next, I summarize the research as discussed in Chapters 3 and 4. On this data, several variation of the signal processing + pattern recognition pipeline for ASP has been tested, which resulted in a generic framework for automated emotion classification with up to 61.31% correct classification of the 4 emotion classes, without the need of personal profiles. Among various other directives for future research, the results emphasize the need for parallel processing of multiple biosignals.

This chapter is a compressed version of:

Broek, E.L. van den, Lisý, V., Janssen, J.H., Westerink, J.D.H.M., Schut, M.H., and Tuinenbreijer, K. (2010). Affective Man-Machine Interface: Unveiling human emotions through biosignals. In A. Fred, J. Filipe & H. Gamboa (Eds.), BioMedical Engineering Systems and Technologies (series: Communications in Computer and Information Science, Vol. 52), p. 21–47. Berlin/Heidelberg, Germany: Springer-Verlag. [invited]