Computational intelligence in emotional or affective systems

Computational Intelligence (CI) methods have shown great capabilities in modeling, prediction, and recognition tasks in DSP and a mature degree of understanding has been achieved in many application areas, in particular in complex multimodal systems supporting ambient human-machine or humanhuman interaction in smart environments, a field that is broadly addressed by the scientific communities and has a strong commercial impact. At the same time, the emotional issue has recently gained increasing attention in Ambient Intelligence (AmI) and smart environments due to its relevance in most common human tasks (like cognitive processes, perception, learning, communication and even “rational” decision-making) and, therefore, is highly relevant for the goal of human-like interaction with machines. The real challenge is taking advantage of the emotional characterization of humans to make the computer interfacing with them more natural and, hence, useful. The scope of this session is to assess to what extent and how sophisticated computational intelligence tools developed so far might support the multidisciplinary research on the characterization of and ambient and system responses to human emotions and expression in interactive scenarios. Scientists working in the field are welcome to provide their contributions on the most recent trends, innovative approaches and future challenges. The session organizers believe to find in WIRN2012 a fruitful scientific scenario to deepen such issues.