Adapting an Anomalous Noise Events Detectorfor Real-Life Operation in the Rome SuburbanPilot Area of the DYNAMAP’s Project
The DYNAMAP project is aimed at implementing a dynamic noise mapping system able to determine the acoustic impact of road infrastructures in real-time, encouraged by the European Noise Directive 2002/49/EC. The noise maps are updated using the information retrieved from a low-cost Wireless Acoustic...
| Autores: | , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2018 |
| País: | España |
| Recursos: | Universitat Ramon Llull (URL) |
| Repositorio: | DAU Arxiu Digital de la Universitat Ramon Llull |
| OAI Identifier: | oai:dau.url.edu:20.500.14342/2895 |
| Acesso em linha: | http://hdl.handle.net/20.500.14342/2895 |
| Access Level: | acceso abierto |
| Palavra-chave: | Contaminació acústica Circulació -- Soroll Soroll urbà |
| Resumo: | The DYNAMAP project is aimed at implementing a dynamic noise mapping system able to determine the acoustic impact of road infrastructures in real-time, encouraged by the European Noise Directive 2002/49/EC. The noise maps are updated using the information retrieved from a low-cost Wireless Acoustic Sensor Network (WASN) deployed in two pilot areas: in the city of Milan (urban) and in the A90 motorway around Rome (suburban). For a proper evaluation of the road infrastructure noise level, the anomalous noise events (ANE) unrelated to traffic noise (e.g. sirens, horns, speech, doors,...) should be removed before updating the noise maps. To that effect, an anomalous noise events detector (ANED) has been designed and trained using data from a real-life recording campaign. In this work, the preliminary version of the ANED algorithm designed for Hi-Cap sensors of the network, and its performance is evaluated and adjusted to conform to the requirements of the final 19-node WASN deployed in the suburban environment. The study is focused on the use of acoustic data in real-life operating conditions and the degree of adaptation of the ANED algorithm for each and every sensor of the WASN deployed in the A90 motorway surrounding Rome. To that end, a two-phase process was conducted: firstly, an study of the preliminary ANED version when running with the operative data from the WASN; and secondly, the production of a new labelled audio dataset of 107 hours that reflects more accurately the real-life WASN conditions were the ANED will operate. |
|---|