Bus travel time prediction based on deep belief network with back-propagation

Chao Chen, Hui Wang, Fang Yuan, Huizhong Jia, Baozhen Yao (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

In an intelligent transportation system, accurate bus information is vital for passengers to schedule their departure time and make reasonable route choice. In this paper, an improved deep belief network (DBN) is proposed to predict the bus travel time. By using Gaussian–Bernoulli restricted Boltzmann machines to construct a DBN, we update the classical DBN to model continuous data. In addition, a back-propagation (BP) neural network is further applied to improve the performance. Based on the real traffic data collected in Shenyang, China, several experiments are conducted to validate the technique. Comparison with typical forecasting methods such as k-nearest neighbor algorithm (k-NN), artificial neural network (ANN), support vector machine (SVM) and random forests (RFs) shows that the proposed method is applicable to the prediction of bus travel time and works better than traditional methods.
Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalNeural Computing and Applications
DOIs
Publication statusE-pub ahead of print - 2 Nov 2019

Fingerprint

Travel time
Bayesian networks
Backpropagation
System buses
Neural networks
Support vector machines
Experiments

Keywords

  • Bus travel time prediction
  • Deep belief network
  • Machine learning models
  • Multi-factor influence

Cite this

Chen, Chao ; Wang, Hui ; Yuan, Fang ; Jia, Huizhong ; Yao, Baozhen. / Bus travel time prediction based on deep belief network with back-propagation. In: Neural Computing and Applications. 2019 ; pp. 1-15.
@article{6e5ff8cba5ce448fb9eda3a92585154d,
title = "Bus travel time prediction based on deep belief network with back-propagation",
abstract = "In an intelligent transportation system, accurate bus information is vital for passengers to schedule their departure time and make reasonable route choice. In this paper, an improved deep belief network (DBN) is proposed to predict the bus travel time. By using Gaussian–Bernoulli restricted Boltzmann machines to construct a DBN, we update the classical DBN to model continuous data. In addition, a back-propagation (BP) neural network is further applied to improve the performance. Based on the real traffic data collected in Shenyang, China, several experiments are conducted to validate the technique. Comparison with typical forecasting methods such as k-nearest neighbor algorithm (k-NN), artificial neural network (ANN), support vector machine (SVM) and random forests (RFs) shows that the proposed method is applicable to the prediction of bus travel time and works better than traditional methods.",
keywords = "Bus travel time prediction, Deep belief network, Machine learning models, Multi-factor influence",
author = "Chao Chen and Hui Wang and Fang Yuan and Huizhong Jia and Baozhen Yao",
year = "2019",
month = "11",
day = "2",
doi = "10.1007/s00521-019-04579-x",
language = "English",
pages = "1--15",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer",

}

Bus travel time prediction based on deep belief network with back-propagation. / Chen, Chao; Wang, Hui; Yuan, Fang; Jia, Huizhong; Yao, Baozhen (Corresponding author).

In: Neural Computing and Applications, 02.11.2019, p. 1-15.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Bus travel time prediction based on deep belief network with back-propagation

AU - Chen, Chao

AU - Wang, Hui

AU - Yuan, Fang

AU - Jia, Huizhong

AU - Yao, Baozhen

PY - 2019/11/2

Y1 - 2019/11/2

N2 - In an intelligent transportation system, accurate bus information is vital for passengers to schedule their departure time and make reasonable route choice. In this paper, an improved deep belief network (DBN) is proposed to predict the bus travel time. By using Gaussian–Bernoulli restricted Boltzmann machines to construct a DBN, we update the classical DBN to model continuous data. In addition, a back-propagation (BP) neural network is further applied to improve the performance. Based on the real traffic data collected in Shenyang, China, several experiments are conducted to validate the technique. Comparison with typical forecasting methods such as k-nearest neighbor algorithm (k-NN), artificial neural network (ANN), support vector machine (SVM) and random forests (RFs) shows that the proposed method is applicable to the prediction of bus travel time and works better than traditional methods.

AB - In an intelligent transportation system, accurate bus information is vital for passengers to schedule their departure time and make reasonable route choice. In this paper, an improved deep belief network (DBN) is proposed to predict the bus travel time. By using Gaussian–Bernoulli restricted Boltzmann machines to construct a DBN, we update the classical DBN to model continuous data. In addition, a back-propagation (BP) neural network is further applied to improve the performance. Based on the real traffic data collected in Shenyang, China, several experiments are conducted to validate the technique. Comparison with typical forecasting methods such as k-nearest neighbor algorithm (k-NN), artificial neural network (ANN), support vector machine (SVM) and random forests (RFs) shows that the proposed method is applicable to the prediction of bus travel time and works better than traditional methods.

KW - Bus travel time prediction

KW - Deep belief network

KW - Machine learning models

KW - Multi-factor influence

UR - http://www.scopus.com/inward/record.url?scp=85074786934&partnerID=8YFLogxK

U2 - 10.1007/s00521-019-04579-x

DO - 10.1007/s00521-019-04579-x

M3 - Article

SP - 1

EP - 15

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

ER -