Full title
Intelligent Multimedia Playback System Based on Brain-Computer Interface and Affective Computing
Duration of project
12/01/2010 – 11/30/2013
Funding source
Swiss National Science Foundation
Description
Emotion is one of the most controversial topics in psychology, a source of intense discussion and disagreement from the earliest philosophers and other intellectuals to the present day. Emotion is generally understood as representing a synthesis of subjective experience, expressive behaviour, and neurochemical activity. Most researchers believe that emotions are part of the human evolutionary legacy and serve adaptive ends by adding to general awareness and the facilitation of social communication. All modern theorists agree that emotions influence what people perceive, learn, and remember, and that they play an important part in personality development.
Over the past years, the volume and pace of BCI research have grown rapidly. In 1995 there were no more than six active BCI research groups, now there are more than 50. They are focusing on brain electrical activity, recorded from the scalp as electroencephalographic activity (EEG) or from within the brain as single-unit activity, as the basis for this new communication and control technology. Currently several new applications for EEG based BCI systems are being studied. Applications such as rehabilitation, multimedia and gaming, neurofeedback etc. are becoming increasingly popular.
In this research, we are interested in studying the possibility for a user to find and consume his/her favorite multimedia content by minimizing interaction with his/her computer, TV, MP3 player, and etc. Personalized content is selected and recommended or displayed to the user who supplies little active information. The recommendation is based on personalized analysis of his/her reactions to the presentation of multimedia content, and his/her patterns of interaction with the interface. We focus on the recommendation of music videos, based on the users emotion level (obtained from physiological and physical state) as well as multimedia content analysis (MCA). In order to elaborate real-time demonstrators, the focus will lie on the development of an automatic and affective music video recommendation system.