The project's objective is to develop a convincing use case in intelligent living-environment monitoring. The technology to be demonstrated in this use case leverages knowledge representation and automated reasoning as means to enable “smart” monitoring of living environments, focusing on urban and social milieu.

All aspects of life are being overseen, monitored, and controlled through hybrid Perception/Analysis/Control (PAC) networks. Software-enabled technology prevails as the ubiquitous glue bringing all aspects of such monitoring to bear on its inner workings. However, human actors bring most, if not all, of the intelligence of such software. With the increased networking of all aspects of society, software intelligence has made great strides in showing a capacity for increased autonomy in the distributed monitoring of PAC networks—the most critical part being the ”A” (Analysis).

This project lies precisely in this line of technologies that attempt to meet the needs for the development of an intelligent monitoring framework that can provide policy makers and analysts with high added-value information. To this aim, the project will propose to combine specific, more semantic-based, techniques for distributed knowledge and information handling developed in areas such as knowledge representation and reasoning, and intelligent query processing. Such could be intuitively illustrated, to give a simple example, by replacing a thermal control system abruptly adjusting the ambient temperature to a higher temperature as the weather chills, to one that does so gradually and preventively by understanding the trend of weather from local data such as temperature, pressure, and precipitations, as well as from the analysis of global networked weather measurements and reports.

Our research objectives address several critical aspects where unified access to distributed information for decentralized monitoring is of central importance, such as: enriching raw data extracted from measurements to enable conflict resolution and easy interpretation; aligning these enriched data with formal models of information quality; representing the meaning of this information with the use of ontologies to support semantic understanding across various domains (e.g., health, transportation, education, etc., ...).