Potential of psychoacoustic descriptors for the occupational noise classification

Authors

  • Raffaele Mariconte DIT, Inail, Roma
  • Giovanni Brambilla DISAT, Università di Milano Bicocca, Milano
  • Maurizio Diano Direzione regionale Calabria, Inail, UOT Catanzaro
  • Diego Annesi DIMEILA, Inail, Roma
  • Claudia Giliberti DIT, Inail, Roma

DOI:

https://doi.org/10.36125/ijoehy.v14i2.501

Keywords:

noise, non-auditory, comfort, exposure, workplaces

Abstract

Occupational noise exposure often contributes to fatigue, tiredness, stress, and annoyance in exposed subjects. These conditions, if prolonged over time, can cause various extra-auditory effects. These effects, associated with sensory overload, may lead exposed people to pay less attention to sounds with important information content (alarms, verbal messages, etc.). The outcome could lead to a reduction in both working performance and safety itself, with potential accident triggering.

This study shows an encouraging result in the use of sound quality metrics and statistical analyses in order to correlate different acoustic descriptors and their role in the classification of the analyzed noise samples, which can be employed to outline a technical and scientific framework to improve the acoustic comfort in working environments and, therefore, to prevent working accidents.

 

 

References

Zwicker E., Fastl H. Psychoacoustics. Facts and models. Berlin, Heidelberg, Springer Ed. 2013

ECMA-418-2, Psychoacoustic metrics for ITT equipment — Part 2 (models based on human perception), Section 5 “A hearing model approach to calculate psychoacoustic parameters”, 2020

Brambilla G., Fiebig A., Measurements and Techniques in Soundscape Research, Chap. 7 in SHAR Handbook on "Soundscapes: Humans and Their Acoustic Environment", vol. 76, Springer Nature, 185-214, April 2023

M. Plata, Deep neural networks with supported clusters preclassification procedure for acoustic scene recognition, Tech. Rep., DCASE2019 Challenge (2019)

M.S. Hossain, G. Muhammad, Environment classification for urban big data using deep learning, IEEE Communications Magazine, 56 (11) (2018), pp. 44-50

R.V. Sharan, T.J. Moir, Acoustic event recognition using cochleagram image and convolutional neural networks, Applied Acoustics, 148 (2019), pp. 62-66

D. Lgs. 81/08 e s.m.i., Nuovo Testo Unico in materia di sicurezza e salute sul lavoro, G.U. n. 101 del 30 aprile 2008

Nordtest Method NT ACOU 112, Acoustics – Prominence of impulsive sounds and for adjustment of LAeq, Taastrup, Denmark, 2002

R. Sottek, Modelle zur Signalverarbeitung im menschlichen Gehör, dissertation, RWTH Aachen, 1993

S. Lê, J. Josse, F. Husson, FactoMineR: A Package for Multivariate Analysis, Journal of Statistical Software, 25(1), 1-18, 2008

A. Kassambara, F. Mundt, Factoextra: Extract and Visualize the Results of Multivariate Data Analyses. R Package Version 1.0.7., 2020

G. Brock, V. Pihur, S. Datta, S. Datta, clValid: An R Package for Cluster Validation, Journal of Statistical Software, 25(4), 1–22, 2008

Downloads

Published

2024-05-13