Home
Research
Members
Publications
Demonstrations
Teaching
Bachelor and Masters
Job Opportunities
Contacts
Centre Universitaire d'Informatique
Université de Genève
CUI - University of Geneva
Battelle Bat. A
7, route de Drize
1227 Carouge 4
Switzerland
Phone: +41 (22) 379 0183
Fax: +41 (22) 379 0250
Secretary: +41 (22) 379 0223
E-mail: guillaume[.]chanel[at]unige[.]ch
Office: #227
Guillaume Chanel obtained an engineering diploma and an MSc degrees in computing and robotics from IMERIR and University of Montpellier, France, in 2002. He obtained his Ph.D. degree in computer science in 2009 at the the University of Geneva where he worked on the automatic assessment of emotions based on EEG and peripheral signals. From 2009 to 2010 he has been a researcher at the KML-Knowledge Media Laboratory, Aalto University, Helsinki, Finland and he is now researcher at the the Computer Vision and Multimedia Laboratory (CVML) and at the Swiss Center for Affective Sciences. His research interests concern the use of physiological measures for improving man-machine interaction. More specifically he is interested in the dynamic adjustment of games mechanic based on players emotions and the inclusion of emotional cues in mediated social interactions.
Since emotions are part of any communication involving human, it is clear that human computer interfaces can benefit from emotion assessment of the user to better react or adapt to his mood. Many studies have invested the use of video or speech to capture facial expressions and emotional states but we believe that physiological signals have the following advantages:
From this point of view, we started to invest the use of these signals for emotion detection. EEG is of particular interest because of the cognitive nature of emotions.
We designed several acquisition protocols and use features from signals of both the peripheral and central nervous system to perform emotional classification tasks. This imply the use of machine learning and pattern recognition algorithms such as LDA, SVM, RVM,… Many fusion strategies between the different signals are also investigated.
Reviewer for: