Anxiety-based affective communication for implicit human-machine interaction

: An implicit human-machine interaction communication framework that is sensitive to human affective states is presented. The overall goal is to achieve detection and recognition of human affect based on physiological signals. This involves building an affect recognition system capable of accepting various physiological parameters as inputs and predicting the probable related affective state. The emphasis of the current work is that of determining the level of anxiety and incorporating this capability into a machine’s decision-making process while interacting with humans. Both regression tree and fuzzy logic methodologies have been investigated for the above task. This paper presents the results of applying the two methods and discusses their comparative merit. Three human participant experiments were designed and trials were conducted with five participants. The experimental results demonstrate the feasibility of the proposed implicit human-machine interaction framework.

• Type: Journal
• Year: 2007
• Where: AEI
• Authors: Pramila Rani, Nilanjan Sarkar, Julie Adams
• Keywords: AEI 2007, Affective State, Human-machine Interaction Communication, Implicit Human-machine Interaction