Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction

As a typical time series, the length of the data sequence is critical to the accuracy of traffic state prediction. In order to fully explore the causality between traffic data, this study established a temporal backtracking and multistep delay model based on recurrent neural networks (RNNs) to learn...

Full description

Saved in:
Bibliographic Details
Main Authors: Licheng Qu, Minghao Zhang, Zhaolu Li, Wei Li
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2020/8899478
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849306806089678848
author Licheng Qu
Minghao Zhang
Zhaolu Li
Wei Li
author_facet Licheng Qu
Minghao Zhang
Zhaolu Li
Wei Li
author_sort Licheng Qu
collection DOAJ
description As a typical time series, the length of the data sequence is critical to the accuracy of traffic state prediction. In order to fully explore the causality between traffic data, this study established a temporal backtracking and multistep delay model based on recurrent neural networks (RNNs) to learn and extract the long- and short-term dependencies of the traffic state data. With a real traffic data set, the coordinate descent algorithm was employed to search and determine the optimal backtracking length of traffic sequence, and multistep delay predictions were performed to demonstrate the relationship between delay steps and prediction accuracies. Besides, the performances were compared between three variants of RNNs (LSTM, GRU, and BiLSTM) and 6 frequently used models, which are decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), random forest (RF), gradient boosting decision tree (GBDT), and stacked autoencoder (SAE). The prediction results of 10 consecutive delay steps suggest that the accuracies of RNNs are far superior to those of other models because of the more powerful and accurate pattern representing ability in time series. It is also proved that RNNs can learn and mine longer time dependencies.
format Article
id doaj-art-278c07a3b9d4487cb35fc2ccee04b3f0
institution Kabale University
issn 0197-6729
2042-3195
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-278c07a3b9d4487cb35fc2ccee04b3f02025-08-20T03:54:57ZengWileyJournal of Advanced Transportation0197-67292042-31952020-01-01202010.1155/2020/88994788899478Temporal Backtracking and Multistep Delay of Traffic Speed Series PredictionLicheng Qu0Minghao Zhang1Zhaolu Li2Wei Li3School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, ChinaSchool of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaAs a typical time series, the length of the data sequence is critical to the accuracy of traffic state prediction. In order to fully explore the causality between traffic data, this study established a temporal backtracking and multistep delay model based on recurrent neural networks (RNNs) to learn and extract the long- and short-term dependencies of the traffic state data. With a real traffic data set, the coordinate descent algorithm was employed to search and determine the optimal backtracking length of traffic sequence, and multistep delay predictions were performed to demonstrate the relationship between delay steps and prediction accuracies. Besides, the performances were compared between three variants of RNNs (LSTM, GRU, and BiLSTM) and 6 frequently used models, which are decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), random forest (RF), gradient boosting decision tree (GBDT), and stacked autoencoder (SAE). The prediction results of 10 consecutive delay steps suggest that the accuracies of RNNs are far superior to those of other models because of the more powerful and accurate pattern representing ability in time series. It is also proved that RNNs can learn and mine longer time dependencies.http://dx.doi.org/10.1155/2020/8899478
spellingShingle Licheng Qu
Minghao Zhang
Zhaolu Li
Wei Li
Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
Journal of Advanced Transportation
title Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
title_full Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
title_fullStr Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
title_full_unstemmed Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
title_short Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
title_sort temporal backtracking and multistep delay of traffic speed series prediction
url http://dx.doi.org/10.1155/2020/8899478
work_keys_str_mv AT lichengqu temporalbacktrackingandmultistepdelayoftrafficspeedseriesprediction
AT minghaozhang temporalbacktrackingandmultistepdelayoftrafficspeedseriesprediction
AT zhaoluli temporalbacktrackingandmultistepdelayoftrafficspeedseriesprediction
AT weili temporalbacktrackingandmultistepdelayoftrafficspeedseriesprediction