We propose to study the notion of intelligent environment as a support to pervasive environments. Our proposed study assumes that a pervasive and ubiquitous multi-agent infrastructure is pervasively deployed in the environment and accessible to users by means of devices that can access internet such as smart phones.
The data produced by the telecare sensors feed the distributed multi agent infrastructure. The intelligent agents deployed in the multi agent infrastructure will use the data to pre-diagnose possible conditions and alert a doctor in charge of the patient.
The proposal's research program plans to illustrate how, by using intelligent cognitive agents deployed in a distributed agent environment, we can improve the current approach to pervasive intelligence from the perspectives of efficiency, interoperability, reliability and openness.
The concrete objectives of the DAEDS project will be the following ones:
- Model the events that are necessary to monitor in the real world and that are relevant to the agent environment.
- Model a cognitive agent mind for agents as an expert system.
- Create a distributed agent environment that mimics the social and physical environments of real patients.
- Decide a set of standards that doctors and hospitals will use to monitor the patients.
- Revise current existing agent platforms and identify their weaknesses, possibly creating a new platform respecting the following characteristics: Lightweightness, Fast Discovery of resources, High Levels of Security, Interoperability.
- Develop a declarative approach, a truly BDI agent mind for planning within distributed agent environments.
- Study the issue of self-organising agent environments.
Publications concerning this project are available on http://publications.hevs.ch/index.php/topics/single/91