A Generic Architecture for Human-Aware Ambient Computing

Abstract

A reusable agent-based generic model is presented for a specific class of Ambient Intelligence applications: those cases addressing human wellbeing and functioning from a human-like understanding. The model incorporates ontologies, knowledge and dynamic models from human-directed sciences such as psychology, social science, neuroscience and biomedical sciences. The model has been formally specified, and it is shown how for specific applications it can be instantiated by application-specific elements, thus providing an executable specification that can be used for prototyping. Moreover, it is shown how dynamic properties can be formally specified and verified against generated traces. IntroductionThe environment in which humans operate has an important influence on their wellbeing and performance. For example, a comfortable workspace or an attentive partner may contribute to good performance or prevention of health problems. Recent developments within Ambient Intelligence provide technological possibilities to contribute to such personal care; cf. [Aarts et al. (2003)], [Aarts et al. (2001)], [Riva et al. (2005)]. For example, our car may warn us when we are falling asleep while driving or when we are too drunk to drive. Such applications can be based on possibilities to acquire sensor information about humans and their functioning, but more substantial applications depend on the availability of adequate knowledge for analysis of information about human functioning. If knowledge about human functioning is represented in a formal and computational format in devices in the environment, these devices can show more human-like understanding, and (re)act accordingly by undertaking actions in a knowledgeable manner that improve the human's wellbeing and performance. As another example, the workspaces of naval officers may in-

A Multi-agent Model for Emotion Contagion Spirals Integrated within a Supporting Ambient Agent Model

“…The generic agent model for human-aware ambient intelligence applications described in [4] was taken as a point of departure, as also was chosen in [6]. One of the possible applications of the resulting ambient agent model could be analyzing and supporting group emotion in virtual meetings.…”

“…As an input for the predictions the concept expressed emotion level (ε S q A ) is used: the emotion level that can be observed from someone's face, for example, by use of a face reader. To integrate the emotion contagion spiral model within an agent model, a generic agent model for human-aware ambient computing (see [4]) was used as a point of departure, as was done in [6].…”

GP-HD: Using Genetic Programming to Generate Dynamical Systems Models for Health Care

“…Unfortunately until now these kind of models need to be specified by exploiting domain knowledge rather than finding relationships in the data automatically (see e.g. [1,20,4,3]). This makes the development time consuming, open to interpretation (as theories are often not precise enough to specify a difference equation), and it does not allow one to find new relationships in the data.…”

A computational model for dynamics of desiring and feeling

“…To obtain an adequate human-aware ambient system, computationally formalised knowledge describing the dynamics and interaction of internal states is needed. To design an ambient system incorporating such a model, agent modelling offers a useful approach, as agents are able to integrate such dynamical models and reason about them (e.g., Bosse, Hoogendoorn, Klein, and Treur, 2009). Human-aware ambient agent systems equipped with the ability to reason about the different types of mental states in principle can be applied to support of humans, for example persons vulnerable to temptations due to a developing addiction.…”