Authors:
Gert-Jan de Vries
and
Marjolein van der Zwaag
Affiliation:
Philips Research Europe, Netherlands
Keyword(s):
Affective computing, Mood, Skin conductance, Algorithm, Parametric model.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Bioinformatics
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Biometrics
;
Biometrics and Pattern Recognition
;
Multimedia
;
Multimedia Signal Processing
;
Pattern Recognition
;
Physiological Processes and Bio-Signal Modeling, Non-Linear Dynamics
;
Real-Time Systems
;
Telecommunications
Abstract:
One of the key challenges in affective computing is the interpretation of physiological signals into affect. Mood, as a subclass of affect, is known to be reflected in skin conductance. While most reports concern strictly controlled laboratory settings, daily life situations pose more challenges in interpreting physiology because more bodily and cognitive processes that influence skin conductivity are involved; for example temperature regulation or physical and mental activity. Existing techniques to reduce the effects of these processes in order to extract mood from skin conductance are rather crude and leave room for improvement. We introduce a more sophisticated method based on skin conductance response subtraction that provides better resemblance with mood. Validation of our method, using comparison with two alternative methods, shows our method excels in differentiation between positive and negative moods from skin conductance. Our method thereby enhances mood extraction from sk
in conductance, thus improving robustness of mood measurements.
(More)