The recent climatic changes imply an increasing manifestation of calamitous phenomena related to important hydrogeological disruptions in many parts of the earth. For this reason, an accurate estimate of rainfall levels becomes essential to be able to warn of the imminent occurrence of a calamitous event and reduce the risk to human beings. This paper proposes an approach based on Convolutional Neural Networks (CNN) to the classification of the audio signal coming from a new rainfall system.

A convolutional neural networks approach to audio classification for rainfall estimation

Avanzato R.;Beritelli F.;
2019-01-01

Abstract

The recent climatic changes imply an increasing manifestation of calamitous phenomena related to important hydrogeological disruptions in many parts of the earth. For this reason, an accurate estimate of rainfall levels becomes essential to be able to warn of the imminent occurrence of a calamitous event and reduce the risk to human beings. This paper proposes an approach based on Convolutional Neural Networks (CNN) to the classification of the audio signal coming from a new rainfall system.
2019
978-1-7281-4069-8
Audio classification; Convolutional Neural Networks; Enviroment sound classification; Feature extraction techniques; Rainfall Estimation
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: https://hdl.handle.net/20.500.11769/409353
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 19
  • ???jsp.display-item.citation.isi??? 12
social impact