In this paper, we propose a Deep Belief Network (DBN) based approach for the classification of audio signals to improve work activity identification and remote surveillance of construction projects. The aim of the work is to obtain an accurate and flexible tool for consistently executing and managing the unmanned monitoring of construction sites by using distributed acoustic sensors. In this paper, ten classes of multiple construction equipment and tools, frequently and broadly used in construction sites, have been collected and examined to conduct and validate the proposed approach. The input provided to the DBN consists in the concatenation of several statistics evaluated by a set of spectral features, like MFCCs and mel-scaled spectrogram. The proposed architecture, along with the preprocessing and the feature extraction steps, has been described in details while the effectiveness of the proposed idea has been demonstrated by some numerical results, evaluated by using real-world recordings. The final overall accuracy on the test set is up to 98% and is a significantly improved performance compared to other state-of-the-are approaches. A practical and real-time application of the presented method has been also proposed in order to apply the classification scheme to sound data recorded in different environmental scenarios.

Deep belief network based audio classification for construction sites monitoring / Scarpiniti, M.; Colasante, F.; Di Tanna, S.; Ciancia, M.; Lee, Y. -C.; Uncini, A.. - In: EXPERT SYSTEMS WITH APPLICATIONS. - ISSN 0957-4174. - 177:(2021), pp. 1-14. [10.1016/j.eswa.2021.114839]

Deep belief network based audio classification for construction sites monitoring

Scarpiniti M.;Uncini A.
2021

Abstract

In this paper, we propose a Deep Belief Network (DBN) based approach for the classification of audio signals to improve work activity identification and remote surveillance of construction projects. The aim of the work is to obtain an accurate and flexible tool for consistently executing and managing the unmanned monitoring of construction sites by using distributed acoustic sensors. In this paper, ten classes of multiple construction equipment and tools, frequently and broadly used in construction sites, have been collected and examined to conduct and validate the proposed approach. The input provided to the DBN consists in the concatenation of several statistics evaluated by a set of spectral features, like MFCCs and mel-scaled spectrogram. The proposed architecture, along with the preprocessing and the feature extraction steps, has been described in details while the effectiveness of the proposed idea has been demonstrated by some numerical results, evaluated by using real-world recordings. The final overall accuracy on the test set is up to 98% and is a significantly improved performance compared to other state-of-the-are approaches. A practical and real-time application of the presented method has been also proposed in order to apply the classification scheme to sound data recorded in different environmental scenarios.
2021
audio processing; construction monitoring; deep belief network (DBN); deep learning; environmental sound classification
01 Pubblicazione su rivista::01a Articolo in rivista
Deep belief network based audio classification for construction sites monitoring / Scarpiniti, M.; Colasante, F.; Di Tanna, S.; Ciancia, M.; Lee, Y. -C.; Uncini, A.. - In: EXPERT SYSTEMS WITH APPLICATIONS. - ISSN 0957-4174. - 177:(2021), pp. 1-14. [10.1016/j.eswa.2021.114839]
File allegati a questo prodotto
File Dimensione Formato  
Scarpiniti_Deep-belief_2021.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.5 MB
Formato Adobe PDF
1.5 MB Adobe PDF   Contatta l'autore
Scarpiniti_postprint_Deep-believe_2021.pdf

accesso aperto

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.8 MB
Formato Adobe PDF
1.8 MB Adobe PDF

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/11573/1535986
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 31
  • ???jsp.display-item.citation.isi??? 26
social impact