Next Article in Journal
A Single Image Enhancement Technique Using Dark Channel Prior
Previous Article in Journal
3D Roughness Measurement of Failure Surface in CFA Pile Samples Using Three-Dimensional Laser Scanning
Article

Traffic Noise Prediction Applying Multivariate Bi-Directional Recurrent Neural Network

1
Center for Low-Emission Transport, AIT Austrian Institute of Technology GmbH, 1210 Vienna, Austria
2
Department of Mechanical Engineering, KU Leuven, 3001 Leuven, Belgium
*
Author to whom correspondence should be addressed.
Academic Editor: Jose Santamaria Lopez
Appl. Sci. 2021, 11(6), 2714; https://doi.org/10.3390/app11062714
Received: 22 February 2021 / Revised: 14 March 2021 / Accepted: 16 March 2021 / Published: 18 March 2021
(This article belongs to the Section Computing and Artificial Intelligence)
With the drastically increasing traffic in the last decades, crucial environmental problems have been caused, such as greenhouse gas emission and traffic noise pollution. These problems have adversely affected our life quality and health conditions. In this paper, modelling of traffic noise employing deep learning is investigated. The goal is to identify the best machine-learning model for predicting traffic noise from real-life traffic data with multivariate traffic features as input. An extensive study on recurrent neural network (RNN) is performed in this work for modelling time series traffic data, which was collected through an experimental campaign at an inner city roundabout, including both video traffic data and audio data. The preprocessing of the data, namely how to generate the appropriate input and output for deep learning model, is detailed in this paper. A selection of different architectures of RNN, such as many-to-one, many-to-many, encoder–decoder architectures, was investigated. Moreover, gated recurrent unit (GRU) and long short-term memory (LSTM) were further discussed. The results revealed that a multivariate bi-directional GRU model with many-to-many architecture achieved the best performance with both high accuracy and computation efficiency. The trained model could be promising for a future smart city concept; with the proposed model, real-time traffic noise predictions can be potentially feasible using only traffic data collected by different sensors in the city, thanks to the generated big data by smart cities. The forecast of excessive noise exposure can help the regulation and policy makers to make early decisions, in order to mitigate the noise level. View Full-Text
Keywords: traffic noise prediction; deep learning; RNN; LSTM; GRU; multivariate traffic noise prediction; deep learning; RNN; LSTM; GRU; multivariate
Show Figures

Figure 1

MDPI and ACS Style

Zhang, X.; Kuehnelt, H.; De Roeck, W. Traffic Noise Prediction Applying Multivariate Bi-Directional Recurrent Neural Network. Appl. Sci. 2021, 11, 2714. https://doi.org/10.3390/app11062714

AMA Style

Zhang X, Kuehnelt H, De Roeck W. Traffic Noise Prediction Applying Multivariate Bi-Directional Recurrent Neural Network. Applied Sciences. 2021; 11(6):2714. https://doi.org/10.3390/app11062714

Chicago/Turabian Style

Zhang, Xue, Helmut Kuehnelt, and Wim De Roeck. 2021. "Traffic Noise Prediction Applying Multivariate Bi-Directional Recurrent Neural Network" Applied Sciences 11, no. 6: 2714. https://doi.org/10.3390/app11062714

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop