The need for noise monitoring and prediction in urban areas is a relevant problem in large cities and growing agglomerations. In fact, besides air pollution and electromagnetic fields, acoustical noise is considered one of the most hazardous agent, in relation to the effects on human health. A large set of predictive models exists in literature, especially for transportation means noise. In this paper, the authors present an innovative approach based on Time Series Analysis (TSA). This kind of models are largely adopted in several disciplines and will show very good performances and adaptability to environmental noise prediction. After a tuning phase, performed on actual data, different validation phases, on different data sets, are presented. Results, expressed in terms of variation between actual data and forecast, show that this model is suitable for almost stationary noise data sets. Finally, an analysis on tuning data set size is performed, giving interesting results and useful advices for model applications to noise assessment.

Acoustic Noise Levels Predictive Model Based on Time Series Analysis

GUARNACCIA, CLAUDIO;QUARTIERI, Joseph;TEPEDINO, CARMINE
2014

Abstract

The need for noise monitoring and prediction in urban areas is a relevant problem in large cities and growing agglomerations. In fact, besides air pollution and electromagnetic fields, acoustical noise is considered one of the most hazardous agent, in relation to the effects on human health. A large set of predictive models exists in literature, especially for transportation means noise. In this paper, the authors present an innovative approach based on Time Series Analysis (TSA). This kind of models are largely adopted in several disciplines and will show very good performances and adaptability to environmental noise prediction. After a tuning phase, performed on actual data, different validation phases, on different data sets, are presented. Results, expressed in terms of variation between actual data and forecast, show that this model is suitable for almost stationary noise data sets. Finally, an analysis on tuning data set size is performed, giving interesting results and useful advices for model applications to noise assessment.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11386/4386253
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact