ExtTra: Short-Term Traffic Flow Prediction Based on Extremely Randomized Trees

Short-term traffic flow prediction is an important task for intelligent transportation systems. Conventional time series based approaches such as ARIMA can hardly reflect the inter-dependence of related roads. Other parametric or nonparametric methods do not take full advantage of the spatial temporal features. Moreover, some machine learning models are still not investigated in solving this problem. To fill this gap, in this paper we propose ExtTra: an extremely randomized trees based approach for short-term traffic flow prediction. To the best of our knowledge, our work is the first effort to apply the extremely randomized trees model on the traffic flow prediction problem. Moreover, our approach incorporates new spatial temporal features which were not considered in previous studies. Experimental results show that our approach significantly outperforms the baselines in prediction accuracy.

[1]  Xun Gong,et al.  Traffic flow forecasting based on hybrid deep learning framework , 2017, 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE).

[2]  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.

[3]  Chang-Tien Lu,et al.  Urban Traffic Flow Prediction Using a Spatio-Temporal Random Effects Model , 2016, J. Intell. Transp. Syst..

[4]  Alessandro De Gloria,et al.  Time-Aware Multivariate Nearest Neighbor Regression Methods for Traffic Flow Prediction , 2015, IEEE Transactions on Intelligent Transportation Systems.

[5]  Said M. Easa,et al.  Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction , 2013, IEEE Transactions on Intelligent Transportation Systems.

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

[7]  Hamidreza Amindavar,et al.  Short-term traffic flow prediction using time-varying Vasicek model , 2017 .

[8]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[9]  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.

[10]  Dong Wang,et al.  Short-Term Traffic Flow Prediction Based on Ensemble Real-Time Sequential Extreme Learning Machine Under Non-Stationary Condition , 2016, 2016 IEEE 83rd Vehicular Technology Conference (VTC Spring).

[11]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[12]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[13]  Lelitha Vanajakshi,et al.  Short-term traffic flow prediction using seasonal ARIMA model with limited input data , 2015, European Transport Research Review.

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

[15]  A. Pascale,et al.  Adaptive Bayesian network for traffic flow prediction , 2011, 2011 IEEE Statistical Signal Processing Workshop (SSP).

[16]  Hashem R Al-Masaeid,et al.  Short-Term Prediction of Traffic Volume in Urban Arterials , 1995 .

[17]  Zili Zhang,et al.  A distributed spatial-temporal weighted model on MapReduce for short-term traffic flow forecasting , 2016, Neurocomputing.