Event Recognition for Intelligent Resource Management
PRONTO emphasizes the role of event recognition in intelligent resource management (IRM) and proposes a methodology for fusing data from various sources, analysing it to extract useful information in the form of events and deliver...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Fecha límite de participación
Sin fecha límite de participación.
Descripción del proyecto
PRONTO emphasizes the role of event recognition in intelligent resource management (IRM) and proposes a methodology for fusing data from various sources, analysing it to extract useful information in the form of events and delivering the resulting knowledge for decision making, through a user-friendly IRM application. In order to achieve this objective, PRONTO draws methods and expertise from the fields of data fusion, information extraction, temporal representation and reasoning, machine learning, and knowledge management systems. PRONTO derives its motivation from the fact that today's organizations collect data in various structured and unstructured formats, but are not able to fully utilize these data to support and improve their resource management process. Therefore, it is evident that the analysis and interpretation of the collected data needs to be automated and transformed into operational knowledge. Events are particularly important pieces of knowledge for resource management. PRONTO proposes the aforementioned synergy of techniques to facilitate the recognition of events from the collected raw data, that remain underutilized with current technologies. The PRONTO methodology to IRM comprises five main steps: (a) Aggregation of data from various sensors and communication between actors, e.g. fire-brigade officers. (b) Analysis of the data and extraction of 'low-level' events. (c) Recognition of 'high-level' events, using Dynamic fine-tuning of event models, using machine learning. The novelty of PRONTO lies in the difficult task of real-time, accurate recognition of complex events given multiple sources of information, including various types of sensor and modes of actor interaction. The usability and acceptance of the derived methods and tools in real-world environments will signal the success of the project. Progress will be measured by real end-users, participating actively, as consortium partners, in all stages of the development of the project.