Machine Learning Prediction of the Long-Term Environmental Acoustic Pattern of a City Location Using Short-Term Sound Pressure Level Measurements

Abstract

To manage noise pollution, cities use monitoring systems over wireless acoustic sensor networks. These networks are mainly composed of fixed-location sound pressure level sensors deployed in outdoor sites of the city for long-term monitoring. However, due to high economic and human resource costs, it is not feasible to deploy fixed metering stations on every street in a city. Therefore, these continuous measurements are usually complemented with short-term measurements at different selected locations, which are carried out by acoustic sensors mounted on vehicles or at street level. In this research, the application of artificial neural networks is proposed for estimation of the long-term environmental acoustic pattern of a location based on the information collected during a short time period. An evaluation has been carried out through a comparison of eight artificial neural network architectures using real data from the acoustic sensor network of Barcelona, Spain, showing higher accuracy in prediction when the complexity of the model increases. Moreover, time slots with better performance can be detected, helping city managers to deploy temporal stations optimally.

Sensors on Internet of Things Systems for the Sustainable Development of Smart Cities: A Systematic Literature Review

“…To monitor urban acoustic environments, people may collect audio data with a microphone [60][61][62]68], remote sonometer (e.g., Model Cesva TA120) [66,69], sound pressure sensors (e.g., MP34DT01) [44]. Yun et al [61] used TDK InvenSense ICS-43434 as a microphone in the Sounds of New York City IoT system.…”

“…Pita et al [66] used the k-means algorithm to cluster behavior patterns of sound pressure levels geographically and temporally, which is effective for analyzing noise data captured by acoustic sensors in Barcelona. Another research work by Navarro and Pita [69] proved that artificial neural networks can predict long-term noise patterns at a location based on short-term measurements. They also emphasized that increasing the number of hidden layers and collecting an hour of data every hour during the 14:00-22:00 time interval can improve the performance of artificial neural networks.…”

Generation and Characteristics of Construction Noise in Rail Transit Engineering Enclosure Structures

“…The most common symptoms include sleep disturbances [48,49], poor concentration [48], headache, head pressure [48], mental fatigue [50], tiredness, irritability [49], and reduced auditory sensitivity [51]. With the rapid development in the fields of deep learning and artificial intelligence, numerous efficient algorithms have demonstrated outstanding performance in noise monitoring and prediction [52,53], emission sound pressure and sound wave control [54,55], as well as the optimization of noise control systems [56,57]. These novel active noise control methods integrated with artificial intelligence effectively overcome the limitations of traditional passive noise control methods in attenuating low-frequency noise, offering new directions for future construction noise control [58,59].…”

Multi-Modal Synthetic Data Fusion and Analysis, Virtual Immersive and Cognitive Neuro-Engineering Technologies, and Bio-inspired Computational Intelligence and Deep Learning Algorithms in the Industrial Metaverse

“…Distributed autonomous control and immersive visualization systems, edge intelligence and data-driven artificial intelligence algorithms, and 3D modeling and simulation technologies (Bordegoni and Ferrise, 2023;Navarro and Pita, 2023;Xian et al, 2023) articulate 3D computer-generated virtual environments in the industrial metaverse. Geolocation data mining and tracking, machine learning-based object recognition and wearable scent technologies, and deep learning and spatial cognition algorithms enable digital hyperrealistic worlds.…”