Adaptive modeling of human responses in complex interaction

Intro: combine strengths of human cognition and evolutionary computing search to efficiently solve problems which neither can do alone Context: develop techniques combining advanced non-intrusive sensor measures of behaviour and emotional reaction in interaction tasks to enable very high level computer support for human goal seeking, in complex data and design environments Outcome: capture a users emotional reactions, overt actions and their preference evaluation to understand complex interactions with the data they view, fuzzy and probability models to accumulate info to identify underlying preferences and extract relationships Benefits: find possible hidden variables which can 'explain' the user's choices or enhance their engagement