In this paper, we describe algorithms developed to analyze physiological signals associated with emotions, in order to recognize the affective states of users via noninvasive technologies. We propose a framework for modeling user's emotions from the sensory inputs and interpretations of our multi-modal system. We also describe examples of circumstances that these systems can be applied to.

In concert with the I/ITSEC ’01 theme, “Warfighting Readiness Through Innovative Training Technology”, this paper explores an innovative approach to enhancing the realism and hence the efficacy of training – developing the capacity for synthetic forces to act and respond emotionally. Emotions, along with moods and dispositions, have been shown to be important determiners of behaviors. They influence how situations are interpreted, how attention is focused, which actions are considered, and how these actions are executed. For example, individuals who are afraid will more readily interpret a situation as dangerous, have their focus of attention narrowed down to the source of their fear, and be biased toward actions that can reduce their level of fear. Similarly, individuals who are angry will more readily interpret others as being hostile, have their focus of attention narrowed down to the source of their anger, and be biased toward aggressive and/or retaliatory actions. Understanding and modeling variations in emotions will be crucial for producing realistic human-like behavior in synthetic forces. The Army has recognized this potential and is now emphasizing the need for such human behavioral characteristics as being vitally important to training. This paper discusses fundamental principles of emotions research and then applies these principles

In this paper, we uncover a new potential application for multi-media technologies: affective intelligent car interfaces for enhanced driving safety. We also describe the experiment we conducted in order to map certain physiological signals (galvanic skin response, heart beat, and temperature) to certain driving-related emotions and states (Frustration/Anger, Panic/Fear, and Boredom/Sleepiness). We demonstrate the results we obtained and describe how we use these results to facilitate a more natural Human-Computer Interaction in our Multimodal Affective Car Interface for the drivers of the future cars. 1

This paper presents an initial evaluation of an emotions model developed for a sophisticated synthetic forces model. Sponsored by ARI, the objective of this research is to make the decision-making process of complex agents less predictable and more realistic, by incorporating emotional factors that affect humans. To this end, we have adopted an approach that promotes the emergence of behavior as a result of complex interactions between factors affecting emotions, integrated in a connectioniststyle model, and factors affecting decision making, represented in a symbolic model.

Abstract. The design of workplaces, namely the physical arrangement of people and machines, has an active influence on work-related issues, such as productivity and efficiency. However, even an ideal physical arrangement of machines is subject to the social and emotional intelligence of the people. It is possible to formalise the former using rules of social order, and to capture the latter using the ideas from Affective Computing. Our intention, then, is to demonstrate that by integrating affective states and participatory/pervasive adaptation of social norms in workplace design, the quality of experience in a working environment can be improved. 1

Abstract not found