The fast expansion of vehicles on the road also paves the way for technology to take advantage of the large amount of data created and put it to use. Sustainable traffic and smart traffic management are sweeping urban areas. Previous research has demonstrated that the spatiotemporal data available can be used to alleviate traffic congestion. The mapping of the GTFS (General Transit Feed Specification) data into a graph structure is emphasised in this work. In order to examine the traffic network, we use Graph Neural Networks (GNNs) in this study and forecast the links between them. To the best of our knowledge, this is one of the first attempts to describe the traffic network as a classification problem rather than a prediction problem, which assuages the challenges posed by the complexity of time and space transfiguration. The study's major goal is to highlight the importance of GTFS feeds that can be obtained from a successful public transit system.
Traffic Congestion Prediction Based on Spatio-Temporal Graph Structure Learning
2023-01-27
378998 byte
Conference paper
Electronic Resource
English
Spatio-temporal graph attention networks for traffic prediction
Taylor & Francis Verlag | 2024
|Short-term traffic congestion prediction with Conv–BiLSTM considering spatio-temporal features
IET | 2021
|Short‐term traffic congestion prediction with Conv–BiLSTM considering spatio‐temporal features
Wiley | 2020
|