In the present work, a crowdsourcing approach is designed, to investigate the correlation between air and noise pollution in urban areas. Citizens are requested to provide air quality measurements and audio recordings using a prototype mobile application specially designed to motivate them to undertake the task of audiovisual capturing. Different use case scenarios of the application are presented, along with the technical specifications and service-based architecture. The UrESC22 dataset is formed, a subset of the ESC50 benchmark dataset consisting of all classes related to polluting activities (vehicles, engines, etc.). The dataset is used to train a convolutional neural network classifier for the detection of audio events related to air pollution.

Authors: Stamatiadou, Marina Eirini; Vryzas, Nikolaos; Vrysis, Lazaros; Saridou, Theodora; Dimoulas, Charalampos
Affiliation: Aristotle University of Thessaloniki, Greece
AES Convention: 152 (May 2022) Paper Number: 10591
Publication Date: May 2, 2022 Import into BibTeX
Subject: Machine Learning / Artificial Intelligence
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=21704

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:   /conv/152/10591.pdf

Start a discussion about this paper!