Weather-Aware Long-Range Traffic Forecast Using Multi-Module Deep Neural Network

Abstract

This study proposes a novel multi-module deep neural network framework which aims at improving intelligent long-term traffic forecasting. Following our previous system, the internal architecture of the new system adds deep learning modules that enable data separation during computation. Thus, prediction becomes more accurate in many sections of the road network and gives dependable results even under possible changes in weather conditions during driving. The performance of the framework is then evaluated for different cases, which include all plausible cases of driving, i.e., regular days, holidays, and days involving severe weather conditions. Compared with other traffic predicting systems that employ the convolutional neural networks, k-nearest neighbor algorithm, and the time series model, it is concluded that the system proposed herein achieves better performance and helps drivers schedule their trips well in advance.

An attention‐based deep learning model for traffic flow prediction using spatiotemporal features towards sustainable smart city

“…This helps to preserve the dependencies among them to predict the crowd flow. Time and weather (TW) aware DNN proposed in Ryu et al 49 predict the traffic flow along with weather information that makes use of weather information, traffic flow, speed, and link information for training.…”

A Review and Analysis of Traffic Data Sources

“…The first operational application of road traffic monitoring is the analysis of the behaviour and regulation of traffic congestion, particularly in urban areas, at traffic light intersections or on high-flow road infrastructures [11][12][13][14]. Directly linked to this application is the opportunity to estimate and predict traffic flows [15][16][17]. A further application is represented by the control of parking and the management of tolls through monitoring parking lots and stall occupancy and facilitating access by users through an information system, as well as the management of parking fees [18][19][20][21].…”