INSYEME (FAR)

Integrated Systems for Emergencies (InSyEme)

Funding programme: Bando GPS MIUR
Start – end year: 2009 – 2013

Partnership
Italdata S.p.a
Innova Consorzio per l’Informatica e la Telematica
Università degli Studi di Firenze Dipartimento di Elettronica e Telecomunicazioni
Consorzio Milano Ricerche
Politecnico di Milano
Università degli Studi di Milano Bicocca

The project

The aim of the project is to study, model and prototype an integrated system to support interventions in case of emergency (INSYEME -Integrated System for Emergency). The system, through the use of new technologies and the implementation of new models, allows the integration of the different  legacy systems used by different operators for emergency management (institutions, local authorities, voluntary organizations) and the subsequent optimization of the response time and the resources used.

The emphasis of the project is on the necessity, in case of a catastrophic event, of having a rapid access to the broadband communication trough an integration with existing communications systems for effective information management. The system is also able to collect and process real-time data provided both by the operators and the different types of sensors located in the area of interest. It also interprets and manages events using computational models in order to optimize the use of resources and to interact efficiently both with remote operations centers and the population.

The technological infrastructure developed can also deliver a wide range of services trough different mobile applications  able to visualize and download real time geo-localized data obtained from sensors.

In this project CMR is involved in the activities regarding : the definition and development of algorithms of distributed data mining and stream mining for real time data elaboration and fusion in order to integrate information of heterogeneous sensors; development of alarm correlation algorithms, in order to continuously update the status of the system; development of time series mining algorithms and scenarios generation in order to extend the classical statistical prediction with an assessment of the likelihood that covers several possible scenarios for the evolution of the environment/system.

Commenti chiusi