Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction

Short-term traffic forecasting based on deep learning methods, especially long short-term memory (LSTM) neural networks, has received much attention in recent years. However, the potential of deep learning methods in traffic forecasting has not yet fully been exploited in terms of the depth of the model architecture, the spatial scale of the prediction area, and the predictive power of spatial-temporal data. In this paper, a deep stacked bidirectional and unidirectional LSTM (SBU- LSTM) neural network architecture is proposed, which considers both forward and backward dependencies in time series data, to predict network-wide traffic speed. A bidirectional LSTM (BDLSM) layer is exploited to capture spatial features and bidirectional temporal dependencies from historical data. To the best of our knowledge, this is the first time that BDLSTMs have been applied as building blocks for a deep architecture model to measure the backward dependency of traffic data for prediction. The proposed model can handle missing values in input data by using a masking mechanism. Further, this scalable model can predict traffic speed for both freeway and complex urban traffic networks. Comparisons with other classical and state-of-the-art models indicate that the proposed SBU-LSTM neural network achieves superior prediction performance for the whole traffic network in both accuracy and robustness.

[1]  Eleni I. Vlahogianni,et al.  Short-term traffic forecasting: Where we are and where we’re going , 2014 .

[2]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Jianhua Guo,et al.  Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification , 2014 .

[4]  S. P. Hoogendoorn,et al.  Freeway Travel Time Prediction with State-Space Neural Networks: Modeling State-Space Dynamics with Recurrent Neural Networks , 2002 .

[5]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[6]  Yajie Zou,et al.  Flexible and Robust Method for Missing Loop Detector Data Imputation , 2015 .

[7]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[9]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[10]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

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

[12]  Fei-Yue Wang,et al.  Travel time prediction with LSTM neural network , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[13]  Dongjoo Park,et al.  Forecasting Freeway Link Travel Times with a Multilayer Feedforward Neural Network , 1999 .

[14]  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).

[15]  W. Y. Szeto,et al.  Short-Term Traffic Speed Forecasting Based on Data Recorded at Irregular Intervals , 2010, IEEE Transactions on Intelligent Transportation Systems.

[16]  Tara N. Sainath,et al.  Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[19]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[20]  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).

[21]  Jan-Ming Ho,et al.  Travel time prediction with support vector regression , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[22]  Hojjat Adeli,et al.  Wavelet Packet‐Autocorrelation Function Method for Traffic Flow Pattern Analysis , 2004 .

[23]  Ardeshir Faghri,et al.  APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS TO INTELLIGENT VEHICLE-HIGHWAY SYSTEMS , 1994 .

[24]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[25]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[26]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  J. Schmidhuber,et al.  A First Look at Music Composition using LSTM Recurrent Neural Networks , 2002 .

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

[29]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[30]  Qi-Rong Qiu,et al.  Short-term wind speed forecasting combined time series method and arch model , 2012, 2012 International Conference on Machine Learning and Cybernetics.

[31]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[32]  Shing Chung Josh Wong,et al.  Urban traffic flow prediction using a fuzzy-neural approach , 2002 .

[33]  Zhiyong Cui,et al.  New progress of DRIVE Net: An E-science transportation platform for data sharing, visualization, modeling, and analysis , 2016, 2016 IEEE International Smart Cities Conference (ISC2).

[34]  Haitham Al-Deek,et al.  Predictions of Freeway Traffic Speeds and Volumes Using Vector Autoregressive Models , 2009, J. Intell. Transp. Syst..

[35]  Yiannis Kamarianakis,et al.  Characterizing regimes in daily cycles of urban traffic using smooth-transition regressions , 2010 .

[36]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[37]  Xuan Song,et al.  DeepTransport: Prediction and Simulation of Human Mobility and Transportation Mode at a Citywide Level , 2016, IJCAI.

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

[39]  Xiaoping Zheng,et al.  An overview of accident forecasting methodologies , 2009 .

[40]  Zhiyong Cui,et al.  Digital roadway interactive visualization and evaluation network applications to WSDOT operational data usage. , 2016 .

[41]  H. M. Zhang,et al.  Fundamental Diagram of Traffic Flow , 2011 .

[42]  Xiaolei Ma,et al.  DRIVE Net , 2011 .

[43]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[44]  Navdeep Jaitly,et al.  Hybrid speech recognition with Deep Bidirectional LSTM , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[45]  Zachary Chase Lipton A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.