Domenico De Salvio

Dr. Domenico De Salvio

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
PDF file
DSDomenico De Salvio
Domenico De Salvio
MBMichael J. Bianco
Michael J. Bianco
PGPeter Gerstoft
Peter Gerstoft
Dario D'OrazioDario D'Orazio
Dario D'Orazio
Massimo GaraiMassimo Garai
Massimo Garai
Noise exposure influences the comfort and well-being of people in several contexts, such as work or learning environments. For instance, in offices, different kind of noises can increase or drop the employees' productivity. Thus, the ability of separating sound sources in real contexts plays a key role in assessing sound environments. Long-term monitoring provide large amounts of data that can be analyzed through machine and deep learning algorithms. Based on previous works, an entire working day was recorded through a sound level meter. Both sound pressure levels and the digital audio recording were collected. Then, a dual clustering analysis was carried out to separate the two main sound sources experienced by workers: traffic and speech noises. The first method exploited the occurrences of sound pressure levels via Gaussian mixture model and K-means clustering. The second analysis performed a semi-supervised deep clustering analyzing the latent space of a variational autoencoder. Results show that both approaches were able to separate the sound sources. Spectral matching and the latent space of the variational autoencoder validated the assumptions underlying the proposed clustering methods.

13 March 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Giulia FratoniGiulia Fratoni
Giulia Fratoni
DSDomenico De Salvio
Domenico De Salvio
VTVirginia Tardini
Virginia Tardini
Massimo GaraiMassimo Garai
Massimo Garai
Paolo ValdiserriPaolo Valdiserri
Paolo Valdiserri
Dario D'OrazioDario D'Orazio
Dario D'Orazio
This document provides a comprehensive overview of in-field measurements of acoustic and environmental conditions in three university lecture halls, focusing on their impact on student activity levels. The study, conducted at the University of Bologna, aims to measure student activity (SA) levels under unfavorable comfort conditions: high occupancy density, low teacher intelligibility, and absence of ventilation. The measurements show that, under these conditions, the student activity level is neither correlated with the room’s thermo-hygrometric conditions nor occupancy levels. The results, on the other hand, indicate that there is an inverse relationship between the SA level and occupancy: the higher the occupancy, the lower the SA level. Under conditions of high occupancy density and suboptimal thermal conditions, the mechanisms underlying student activity appear to differ from those observed in previous studies conducted under lower occupancy density. In the latter, an increase in SA levels was measured as occupancy increased. In contrast, the present study highlights an inverse behavior where students tend to reduce their activity as the number of students increases.