Unidirectional and Bidirectional LSTM Models for Short-Term Traffic Prediction

Rusul Abduljabbar; Hussein Dia; Pei-Wei Tsai

doi:10.1155/2021/5589075

journal article Open Access Mar 26, 2021

Unidirectional and Bidirectional LSTM Models for Short-Term Traffic Prediction

Rusul Abduljabbar

Hussein Dia

Pei-Wei Tsai

Journal of Advanced Transportation Vol. 2021 pp. 1-16 · Wiley

View at Publisher Save 10.1155/2021/5589075

Abstract

This paper presents the development and evaluation of short-term traffic prediction models using unidirectional and bidirectional deep learning long short-term memory (LSTM) neural networks. The unidirectional LSTM (Uni-LSTM) model provides high performance through its ability to recognize longer sequences of traffic time series data. In this work, Uni-LSTM is extended to bidirectional LSTM (BiLSTM) networks which train the input data twice through forward and backward directions. The paper presents a comparative evaluation of the two models for short-term speed and traffic flow prediction using a common dataset of field observations collected from multiple freeways in Australia. The results showed BiLSTM performed better for variable prediction horizons for both speed and flow. Stacked and mixed Uni-LSTM and BiLSTM models were also investigated for 15-minute prediction horizons resulting in improved accuracy when using 4-layer BiLSTM networks. The optimized 4-layer BiLSTM model was then calibrated and validated for multiple prediction horizons using data from three different freeways. The validation results showed a high degree of prediction accuracy exceeding 90% for speeds up to 60-minute prediction horizons. For flow, the model achieved accuracies above 90% for 5- and 10-minute prediction horizons and more than 80% accuracy for 15- and 30-minute prediction horizons. These findings extend the set of AI models available for road operators and provide them with confidence in applying robust models that have been tested and evaluated on different freeways in Australia.

Topics

No keywords indexed for this article. Browse by subject →

References

46

[1]

H. Dia "Dynamics of drivers’ route choice decisions under advanced traveller information systems" Road & Transport Research (2001)

[2]

10.11175/easts.13.1785

[3]

R. Abduljabbar "A deep learning approach for freeway vehicle speed and flow prediction"

[4]

K. Thomas "January. Simulation of arterial incident detection using neural networks"

[5]

10.1016/s0386-1112(14)60115-1

[6]

K. Thomas "Comparative evaluation of freeway incident detection models using field data" IEE Proceedings-Intelligent Transport Systems (2006) 10.1049/ip-its:20055015

[7]

10.1109/tits.2016.2643005

[8]

Traffic flow prediction based on combination of support vector machine and data denoising schemes

Jinjun Tang, Xinqiang Chen, Zheng Hu et al.

Physica A: Statistical Mechanics and its Applicati... 10.1016/j.physa.2019.03.007

[9]

H. Dia "Comparative performance of freeway automated incident detection algorithms" (1996)

[10]

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

Xiaolei Ma, Zhimin Tao, Yinhai Wang et al.

Transportation Research Part C: Emerging Technolog... 10.1016/j.trc.2015.03.014

[11]

LSTM network: a deep learning approach for short‐term traffic forecast

Zheng Zhao, Weihai Chen, Xingming Wu et al.

IET Intelligent Transport Systems 10.1049/iet-its.2016.0208

[12]

D. Kang "Short-term traffic flow prediction with LSTM recurrent neural network"

[13]

H. Zou "Short-term traffic flow prediction based on PCC-BiLSTM"

[14]

J. Wang "Deep bi-directional long short-term memory model for short-term traffic flow prediction"

[15]

10.1177/0361198120927393

[16]

S. Siami-Namini "The performance of LSTM and BiLSTM in forecasting time series"

[17]

10.3390/su11010189

[18]

Y. Duan "Travel time prediction with LSTM neural network"

[19]

G. Song "An on-road wireless sensor network approach for urban traffic state monitoring"

[20]

10.1198/jasa.2007.s209

[21]

M. G. Karlaftis "Memory properties and fractional integration in transportation time-series" Transportation Research Part C: Emerging Technologies (2009) 10.1016/j.trc.2009.03.001

[22]

G. Fusco "Short-term speed predictions exploiting big data on large urban road networks" Transportation Research Part C: Emerging Technologies (2016) 10.1016/j.trc.2016.10.019

[23]

C. Chen "Short-time traffic flow prediction with ARIMA-GARCH model"

[24]

J. Guo "Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification" Transportation Research Part C: Emerging Technologies (2014) 10.1016/j.trc.2014.02.006

[25]

M. Lippi "Short-term traffic flow forecasting: an experimental comparison of time-series analysis and supervised learning" IEEE Transactions on Intelligent Transportation Systems (2013) 10.1109/tits.2013.2247040

[26]

J. Morton "Analysis of recurrent neural networks for probabilistic modeling of driver behavior" IEEE Transactions on Intelligent Transportation Systems (2016) 10.1109/tits.2016.2603007

[27]

H. Shao "Traffic flow prediction with long short-term memory networks (LSTMs)"

[28]

Q. Zhaowei "Short-term traffic flow forecasting method with MB-LSTM hybrid network" IEEE Transactions on Intelligent Transportation Systems (2020) 10.1109/tits.2020.3009725

[29]

Z. Cui "Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction" (2018)

[30]

M. Lu "DeepBSTN: a deep bidirection network model for urban traffic prediction"

[31]

K. Yeon "Ego-vehicle speed prediction using a long short-term memory based recurrent neural network" International Journal of Automotive Technology (2019) 10.1007/s12239-019-0067-y

[32]

10.1155/2020/8953182

[33]

10.1016/j.matcom.2019.12.013

[34]

M. Farahani "Short-term traffic flow prediction using variational LSTM networks" (2020)

[35]

10.1155/2020/1434080

[36]

P. Poonia "Short-term traffic flow prediction: using LSTM"

[37]

C. Kang "Application of LSTM in short-term traffic flow prediction"

[38]

10.1016/j.aej.2020.06.008

[39]

10.1109/tfuzz.2020.2986995

[40]

10.1016/s0377-2217(00)00125-9

[41]

10.1016/s0968-090x(97)00016-8

[42]

D. T. Larose (2014) 10.1002/9781118874059

[43]

10.1007/s12239-019-0067-y

[44]

C. Sutandi "Performance evaluation of an advanced traffic control system in a developing country"

[45]

S. Panwai "Development and evaluation of a reactive agent-based car following model"

[46]

K. Thomas "Simulation of arterial incident detection using neural networks"

Metrics

110

Citations

46

References

Details

Published: Mar 26, 2021
Vol/Issue: 2021
Pages: 1-16
License: View

Authors

R

Rusul Abduljabbar

Department of Civil and Construction Engineering, Swinburne University of Technology, Melbourne, Australia

H

Hussein Dia

Department of Civil and Construction Engineering, Swinburne University of Technology, Melbourne, Australia

P

Pei-Wei Tsai

Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia

Cite This Article

Rusul Abduljabbar, Hussein Dia, Pei-Wei Tsai (2021). Unidirectional and Bidirectional LSTM Models for Short-Term Traffic Prediction. Journal of Advanced Transportation, 2021, 1-16. https://doi.org/10.1155/2021/5589075

Unidirectional and Bidirectional LSTM Models for Short-Term Traffic Prediction

You May Also Like