Open AccessShort‐term prediction of traffic flow under incident conditions using graph convolutional recurrent neural network and traffic simulation
Author(s) -
Fukuda Shota,
Uchida Hideaki,
Fujii Hideki,
Yamada Tomonori
Publication year - 2020
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/iet-its.2019.0778
Subject(s) - traffic flow (computer networking) , computer science , traffic generation model , deep learning , graph , convolutional neural network , traffic congestion reconstruction with kerner's three phase theory , network traffic simulation , term (time) , artificial intelligence , floating car data , data mining , artificial neural network , data modeling , machine learning , real time computing , traffic congestion , network traffic control , engineering , computer network , transport engineering , theoretical computer science , physics , quantum mechanics , database , network packet
The objective of the study is to predict traffic flow under unusual conditions by using a deep learning model. Conventionally, machine‐learning‐based traffic prediction is frequently carried out. Model learning requires large amounts of training data; however, collecting sufficient samples is a challenge in the event of traffic incidents. To address this challenge, large amounts of traffic data were generated by performing traffic simulations under various traffic incidents. These data were used as training data, and a deep learning model with graph convolution and input of traffic incident information features was proposed. Subsequently, the prediction accuracy was compared with other models such as long short‐term memory, which is typically used in traffic prediction. The results demonstrated the superiority of the proposed model in representing phenomena with strong spatio‐temporal dependencies, such as traffic flow, and its effectiveness in traffic prediction.