In this paper, were conducted a study on the noise produced by traffic on the freeway. In particular, it was rated the Sound Pressure Level Equivalent, resulting from the passage of vehicles on a highway located in southern Italy. It was carried out a number of readings using five sensors Orione Cel 500 Model 573 located close to the highway. The period of data collection lasted about six months and involved a stretch of about 20 km. In addition, the following atmosphere and environmental parameters were detected: Speed and Wind Direction, Temperature, Rainfall, and Traffic Flow. The data, organized and stored in an appropriately trained GIS system, were processed using Artificial Neural Network procedures. The Artificial Neural Network has proved particularly valid in fact, in comparison with the main models in the literature it was the most reliable.
Evaluating Freeway Traffic Noise Using Artificial Neural Network / Daiva, Žilionienė; Mario De, Luca; Dell'Acqua, Gianluca; Lamberti, Renato; Biancardo, Salvatore Antonio; Russo, Francesca. - Section: Roads and Railways:(2014), pp. 1-9. (Intervento presentato al convegno 9th International Conference “Environmental Engineering” tenutosi a Vilnius nel 22–23 May 2014).
Evaluating Freeway Traffic Noise Using Artificial Neural Network
DELL'ACQUA, GIANLUCA;LAMBERTI, RENATO;Biancardo, Salvatore Antonio;RUSSO, FRANCESCA
2014
Abstract
In this paper, were conducted a study on the noise produced by traffic on the freeway. In particular, it was rated the Sound Pressure Level Equivalent, resulting from the passage of vehicles on a highway located in southern Italy. It was carried out a number of readings using five sensors Orione Cel 500 Model 573 located close to the highway. The period of data collection lasted about six months and involved a stretch of about 20 km. In addition, the following atmosphere and environmental parameters were detected: Speed and Wind Direction, Temperature, Rainfall, and Traffic Flow. The data, organized and stored in an appropriately trained GIS system, were processed using Artificial Neural Network procedures. The Artificial Neural Network has proved particularly valid in fact, in comparison with the main models in the literature it was the most reliable.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
