Metric-Based Multi-Task Grouping Neural Network for Traffic Flow Forecasting

Traffic flow forecasting is a fundamental problem in transportation modeling and management. Among various methods multi-task neural network has been demonstrated to be a promising and effective model for traffic flow forecasting, while there are still two issues unconsidered: 1) learning unrelated tasks together tends to reduce the model’s performance; 2) how to define or learn the distance metric for distinguishing related tasks and unrelated tasks. In this paper, a metric learning based K-means method is proposed to group related tasks together which effectively reduces the semantic gap between domain knowledge and handcrafted feature engineering. Then for each group of tasks, a deep neural network is built for traffic flow forecasting. Experimental results show the metric-based grouping method clusters tasks more reasonably with a better metric than classic Euclidean-based K-means. The final results of traffic flow forecasting on real dataset show the metric-based multi-task neural network outperforms the Euclidean-based multi-task neural network.

[1]  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.

[2]  Shiliang Sun.  Traffic flow forecasting based on multitask ensemble learning , 2009, GEC '09.

[3]  Shiliang Sun,et al.  A bayesian network approach to traffic flow forecasting , 2006, IEEE Transactions on Intelligent Transportation Systems.

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

[5]  Wanli Min,et al.  Real-time road traffic prediction with spatio-temporal correlations , 2011 .

[6]  Feifeng Zheng,et al.  Forecasting urban traffic flow by SVR with continuous ACO , 2011 .

[7]  Mu-Chen Chen,et al.  Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks , 2012 .

[8]  Thomas Urbanik,et al.  Short-Term Freeway Traffic Volume Forecasting Using Radial Basis Function Neural Network , 1998 .

[9]  Brian Kulis,et al.  Metric Learning: A Survey , 2013, Found. Trends Mach. Learn..

[10]  Hojjat Adeli,et al.  Dynamic Wavelet Neural Network Model for Traffic Flow Forecasting , 2005 .

[11]  Shiliang Sun,et al.  Network-Scale Traffic Modeling and Forecasting with Graphical Lasso and Neural Networks , 2012, ArXiv.

[12]  Billy M. Williams,et al.  Comparison of parametric and nonparametric models for traffic flow forecasting , 2002 .

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

[14]  A. R. Cook,et al.  ANALYSIS OF FREEWAY TRAFFIC TIME-SERIES DATA BY USING BOX-JENKINS TECHNIQUES , 1979 .

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

[16]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[17]  Lee D. Han,et al.  Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions , 2009, Expert Syst. Appl..

[18]  Roland Chrobok,et al.  Traffic forecast using simulations of large scale networks , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[19]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[20]  Shiliang Sun,et al.  Neural network multitask learning for traffic flow forecasting , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[21]  I Okutani,et al.  Dynamic prediction of traffic volume through Kalman Filtering , 1984 .

[22]  Marc Sebban,et al.  A Survey on Metric Learning for Feature Vectors and Structured Data , 2013, ArXiv.

[23]  Shiliang Sun,et al.  Multi-link traffic flow forecasting using neural networks , 2010, 2010 Sixth International Conference on Natural Computation.