The Life of a New York City Noise Sensor Network

Abstract

Noise pollution is one of the topmost quality of life issues for urban residents in the United States. Continued exposure to high levels of noise has proven effects on health, including acute effects such as sleep disruption, and long-term effects such as hypertension, heart disease, and hearing loss. To investigate and ultimately aid in the mitigation of urban noise, a network of 55 sensor nodes has been deployed across New York City for over two years, collecting sound pressure level (SPL) and audio data. This network has cumulatively amassed over 75 years of calibrated, high-resolution SPL measurements and 35 years of audio data. In addition, high frequency telemetry data have been collected that provides an indication of a sensors’ health. These telemetry data were analyzed over an 18-month period across 31 of the sensors. It has been used to develop a prototype model for pre-failure detection which has the ability to identify sensors in a prefail state 69.1% of the time. The entire network infrastructure is outlined, including the operation of the sensors, followed by an analysis of its data yield and the development of the fault detection approach and the future system integration plans for this.

Low-Cost Sensors for Urban Noise Monitoring Networks—A Literature Review

“…The set of acoustical tests show that the sensor generally meets the Class-2 criteria of the IEC 61672-1 standard [7]. This sensor was recently updated [35], replacing the processing unit by a R-Pi 2 Model B device in order to increase the computational performances and using a digital MEMS in order to reduce the radio-frequency (RF) interference. This sensor was successfully deployed across New-York City, producing a huge acoustic data collection in terms of sound level indicators and audio signal samples.…”

“…Solutions for the implementation of a complete information technology (IT) infrastructure for sensor, network and data management is not developed in this article, as this topic would in itself merit its own literature review in order to address the important issues that are associated (data encryption, privacy, security, scalability, management of a large number of sensors, interfacing, database management, storage, data visualization, etc.). Nevertheless, the reader can already refer to recent publications showing examples of full noise SN deployment [34,35].…”

“…It therefore seems interesting to make a detailed point of current research on this subject, and in particular to highlight the essential characteristics that must be considered for this new generation of acoustic sensors in order to respond to the identified issues and the future ones. Compared to recent articles that already present a review of the existing system [35][36][37][38][39], the present contribution focuses on a detailed analysis of the technical solutions developed in the literature, highlighting their strengths and weaknesses, and showing how the rapid evolution of technologies can now fully meet the requirements for a successful deployment of modern noise SN.…”

Evaluation of Classical Machine Learning Techniques towards Urban Sound Recognition on Embedded Systems

“…A system for monitoring, analysis and mitigation of urban noise pollution is proposed in [9,10] as part of the SOunds of New York City (SONYC) project. A Raspberry Pi-based system acting as WSN nodes performs continuous Sound Pressure Level (SPL) measurements while acquiring, compressing and transmitting 10-second audio snippets at random intervals.…”

Wireless Acoustic Sensor Nodes for Noise Monitoring in the City of Linares (Jaén)

“…Based on the two classifications presented in the literature [37,38], the system is characterized by the following: (a) high data quality; (b) easily scalable to a large number of nodes; (c) can work continuously for long periods of time; (d) affordability due to its low-cost equipment; (e) data accessibility through a cloud web server; (f) the capacity to perform spectral analysis calculations, compute L AeqT , and conduct real-time signal processing; and (g) high computational capacity and low-cost equipment.…”