Low-Cost Distributed Acoustic Sensor Network for Real-Time Urban Sound Monitoring

Ester Vidaña-Vila,Joan Navarro,Rosa Ma Alsina-Pagès,Dan Stowell,Cristina Borda-Fortuny

doi:10.3390/electronics9122119

Ester Vidaña-Vila, Joan Navarro + Show 3 more

Open Access

https://doi.org/10.3390/electronics9122119

Copy DOI

Journal: Electronics	Publication Date: Dec 11, 2020
Citations: 11	License type: CC BY 4.0

Affiliation: Barcelona Media, Queen Mary University of London

Abstract

Continuous exposure to urban noise has been found to be one of the major threats to citizens’ health. In this regard, several organizations are devoting huge efforts to designing new in-field systems to identify the acoustic sources of these threats to protect those citizens at risk. Typically, these prototype systems are composed of expensive components that limit their large-scale deployment and thus reduce the scope of their measurements. This paper aims to present a highly scalable low-cost distributed infrastructure that features a ubiquitous acoustic sensor network to monitor urban sounds. It takes advantage of (1) low-cost microphones deployed in a redundant topology to improve their individual performance when identifying the sound source, (2) a deep-learning algorithm for sound recognition, (3) a distributed data-processing middleware to reach consensus on the sound identification, and (4) a custom planar antenna with an almost isotropic radiation pattern for the proper node communication. This enables practitioners to acoustically populate urban spaces and provide a reliable view of noises occurring in real time. The city of Barcelona (Spain) and the UrbanSound8K dataset have been selected to analytically validate the proposed approach. Results obtained in laboratory tests endorse the feasibility of this proposal.

Highlights

IntroductionNoise can negatively affect sleep quality [3], induce chronic effects on the nervous sympathetic system [4], or even cause psycho-physiological effects such as annoyance, reduced performance or aggressive behavior [5]
Research dating back to the last century [1] has acknowledged that continuous exposure to high levels of noise is harmful for human beings, as recently highlighted by the World Health Organization (WHO) [2]
This work aims to extrapolate this idea to the field of urban sound monitoring, i.e., the use of a set of low-cost microphones deployed in a redundant topology—being the sensing layer [12] of an ubiquitous sensor network that will later provide them with additional storage and computing features—to listen to events from large-scale areas in a cost-effective way while obtaining a reasonable accuracy

Summary

Introduction

Noise can negatively affect sleep quality [3], induce chronic effects on the nervous sympathetic system [4], or even cause psycho-physiological effects such as annoyance, reduced performance or aggressive behavior [5] In this context, noise is often defined as a type of unwanted and/or harmful sound that disturbs communication between individuals [5,6], i.e., the overall acoustic energy measured in Sound. The WHO recommends that noise must be below 35 dBA in classrooms to enable good teaching and learning conditions, or below 30 dBA in bedrooms to enable good quality sleep [8] Most of these regulations define the maximum level of noise allowed in a specific

Objectives

Methods

Findings

Discussion

Conclusion