Using Deep Learning to Predict Short Term Traffic Flow: A Systematic Literature Review

This paper systematically reviews Deep Learning-based methods for traffic flow prediction. We extracted 26 articles using a concrete methodology and reviewed them from two perspectives: first, the deep learning architecture used; and second, the datasets and data dimensions incorporated. Recent big data explosion caused by sensors, IoV, IoT and GPS technology needs traffic analytics using deep architectures. This survey reveals that the LSTM (Long Short-Term Memory) Neural Networks are the most commonly used architecture for short term traffic flow prediction due to their inherent ability to handle sequential data. Among the datasets, PeMS is the most commonly used for traffic flow prediction task. Today, Intelligent Transport Systems (ITS) are not limited to temporal data; spatial dimension is also incorporated along with weather data, and traffic sentiments from twitter, Facebook and Instagram to get better results. In the authors’ knowledge, this is the first deep learning review in ITS domain.

[1]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[2]  V LeelavathiM,et al.  AN ARCHITECTURE OF DEEP LEARNING METHOD TO PREDICT TRAFFIC FLOW IN BIG DATA , 2016 .

[3]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[4]  Li Li,et al.  Using LSTM and GRU neural network methods for traffic flow prediction , 2016, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).

[5]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction , 2013, ADMA.

[6]  Ridha Soua,et al.  Improving Traffic Flow Prediction With Weather Information in Connected Cars: A Deep Learning Approach , 2016, IEEE Transactions on Vehicular Technology.

[7]  M. Beynon,et al.  The Dempster-Shafer theory of evidence: an alternative approach to multicriteria decision modelling , 2000 .

[8]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

[9]  Arief B. Koesdwiady,et al.  Big-data-generated traffic flow prediction using deep learning and dempster-shafer theory , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[10]  Nicholas G. Polson,et al.  Deep learning for short-term traffic flow prediction , 2016, 1604.04527.

[11]  Shiv Surya,et al.  TraCount: a deep convolutional neural network for highly overlapping vehicle counting , 2016, ICVGIP '16.

[12]  Fei-Yue Wang,et al.  Long short-term memory model for traffic congestion prediction with online open data , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[13]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[14]  Chris Tofallis,et al.  Erratum: A better measure of relative prediction accuracy for model selection and model estimation , 2015, J. Oper. Res. Soc..

[15]  Yunpeng Wang,et al.  Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory , 2015, PloS one.

[16]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[17]  Michel Verleysen,et al.  The Curse of Dimensionality in Data Mining and Time Series Prediction , 2005, IWANN.

[18]  Stephan Pieper,et al.  Traffic Prediction using a Deep Learning Paradigm , 2017, EDBT/ICDT Workshops.

[19]  G. Antes,et al.  Five Steps to Conducting a Systematic Review , 2003 .

[20]  Peter C. Y. Chen,et al.  LSTM network: a deep learning approach for short-term traffic forecast , 2017 .

[21]  Huachun Tan,et al.  Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework , 2016, ArXiv.

[22]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[23]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[24]  Jianping Wu,et al.  Traffic speed prediction using deep learning method , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[25]  Fei-Yue Wang,et al.  An efficient realization of deep learning for traffic data imputation , 2016 .

[26]  Wen-Chih Peng,et al.  Exploring Spatio-Temporal Features for Traffic Estimation on Road Networks , 2009, SSTD.

[27]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[28]  Ugur Demiryurek,et al.  Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting , 2017, SDM.

[29]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[30]  Junjie Wu,et al.  Traffic Speed Prediction and Congestion Source Exploration: A Deep Learning Method , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[31]  Fei-Yue Wang,et al.  Performance evaluation of the deep learning approach for traffic flow prediction at different times , 2016, 2016 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI).

[32]  Tharam S. Dillon,et al.  Optimized Structure of the Traffic Flow Forecasting Model With a Deep Learning Approach , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Ying Zhu,et al.  DeepSense: A novel learning mechanism for traffic prediction with taxi GPS traces , 2014, 2014 IEEE Global Communications Conference.

[34]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[35]  Boon-Hee Soong,et al.  Traffic flow prediction with Long Short-Term Memory Networks (LSTMs) , 2016, 2016 IEEE Region 10 Conference (TENCON).

[36]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[37]  R. Bellman.  Dynamic programming. , 1957, Science.

[38]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.