DYNAMAP: A SYSTEM WITH LOW-COST HARDWARE AND ARTIFICIAL INTELLIGENCE TO COMPUTE REAL TIME NOISE MAPS. Referencia PACS: 43.50.Rq

The DYNAMAP project has been approved for co-financing by the European Commission through the Life+ 2013 program last May 2014. DYNAMAP aims at the installation of a prototype system in the municipalities of Rome and Milan. It is based on pervasive low-cost hardware network for noise measurement together with some artificial intelligence algorithm to perform the automatic creation of real time noise maps. This work explains the concept of the project and some technical specifications about the low-cost hardware and the smart detection algorithm that will be implemented to avoid biasing the noise maps with sound events that do not come from road traffic. INTRODUCTION The DYNAMAP project (Dynamic Acoustic Mapping Development of low cost sensors networks for real time noise mapping) aims at developing a dynamic noise mapping system able to detect and represent in real time the acoustic impact due to road infrastructures. Scope of the project is the European Directive 2002/49/EC relating to the assessment and management of environmental noise (END) [1]. In particular, the project refers to the need of updating noise maps every five years, as stated in the END. As a matter of fact, the update of noise maps using a standard approach is time and cost consuming and has a significant impact on the financial statements of the authorities responsible for providing noise maps, such as road administrations and local or central authorities. To ease the update of noise maps and reduce their economic impact, the reiteration of noise mapping activities can be automated developing an integrated system for data acquisition and processing able to detect and report in real time the acoustic impact due to noise sources. The system will be composed by low cost sensors measuring the sound pressure levels emitted by the noise sources present in the area to be mapped and by a software tool based on a GIS platform performing real time noise maps updating. Noise sensors will be based on low power microcontroller systems like the ones used in Noisemote [2].Moreover, the system will be endowed with artificial intelligence capabilities that will allow to detect noise events caused by sources other than road traffic. The objective is that the rendered noise maps will faithfully represent the noise levels caused by road infrastructures solely. This anomalous noise event detection algorithm builds on previous works on environmental sound source recognition and classification [3,4]. 45o CONGRESO ESPAÑOL DE ACÚSTICA 8o CONGRESO IBÉRICO DE ACÚSTICA EUROPEAN SYMPOSIUM ON SMART CITIES AND ENVIRONMENTAL ACOUSTICS