Building sparse models for traffic flow prediction: an empirical comparison between statistical heuristics and geometric heuristics for Bayesian network approaches

ABSTRACT As the sensors become pervasive in transportation systems, traffic prediction becomes more challenging due to the significant increase of data. In this paper, we study how to design BNs for traffic flow prediction with an emphasis on node selection strategy. Three node selection strategies are evaluated based on PeMS (Performance Measurement System) dataset: the Graphical Lasso approach, geographically neighboring approach, and direct correlation approach. Test results show that feeding all the available data into the prediction model might not be a wise choice. The three node selection strategies mentioned above are generally equivalent in prediction performance. We also find that direct correlation approach may lead a sparser model and meanwhile keeps good prediction performance on the PeMS dataset. The obtained conclusions not only help simplify the design of traffic flow prediction models in practice, but also shed light on how to effectively use the massive data.

[1]  Hojjat Adeli,et al.  Neural Networks in Civil Engineering: 1989–2000 , 2001 .

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

[3]  Rod E. Turochy.  Enhancing Short-Term Traffic Forecasting with Traffic Condition Information , 2006 .

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

[5]  Zhiheng Li,et al.  A Comparison of Detrending Models and Multi-Regime Models for Traffic Flow Prediction , 2014, IEEE Intelligent Transportation Systems Magazine.

[6]  Baher Abdulhai,et al.  Distributed maximum likelihood estimation for flow and speed density prediction in distributed traffic detectors with Gaussian mixture model assumption , 2012 .

[7]  Per Högberg,et al.  Estimation of parameters in models for traffic prediction: A non-linear regression approach , 1976 .

[8]  Yanru Zhang,et al.  Stochastic Volatility Modeling Approach that Accounts for Uncertainties in Travel Time Reliability Forecasting , 2014 .

[9]  Yi Zhang,et al.  PPCA-Based Missing Data Imputation for Traffic Flow Volume: A Systematical Approach , 2009, IEEE Transactions on Intelligent Transportation Systems.

[10]  Larry A. Wasserman,et al.  The huge Package for High-dimensional Undirected Graph Estimation in R , 2012, J. Mach. Learn. Res..

[11]  Der-Horng Lee,et al.  Short-term freeway traffic flow prediction : Bayesian combined neural network approach , 2006 .

[12]  B. Basu,et al.  Bayesian Time-Series Model for Short-Term Traffic Flow Forecasting , 2007 .

[13]  Yunlong Zhang,et al.  Freeway Travel Time Prediction Using Takagi–Sugeno–Kang Fuzzy Neural Network , 2013, Comput. Aided Civ. Infrastructure Eng..

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

[15]  Yanru Zhang,et al.  A hybrid short-term traffic flow forecasting method based on spectral analysis and statistical volatility model , 2014 .

[16]  Shiliang Sun,et al.  The Selective Random Subspace Predictor for Traffic Flow Forecasting , 2007, IEEE Transactions on Intelligent Transportation Systems.

[17]  Gopal K. Kanji,et al.  Performance measurement system , 2002 .

[18]  Stephen D. Clark,et al.  Traffic Prediction Using Multivariate Nonparametric Regression , 2003 .

[19]  Xiaosi Zeng,et al.  Development of Recurrent Neural Network Considering Temporal‐Spatial Input Dynamics for Freeway Travel Time Modeling , 2013, Comput. Aided Civ. Infrastructure Eng..

[20]  Shiliang Sun,et al.  Bayesian Network Methods for Traffic Flow Forecasting with Incomplete Data , 2004, ECML.

[21]  Stephen Graham Ritchie,et al.  TRANSPORTATION RESEARCH. PART C, EMERGING TECHNOLOGIES , 1993 .

[22]  Jiaqiu Wang,et al.  A Dynamic Spatial Weight Matrix and Localized Space–Time Autoregressive Integrated Moving Average for Network Modeling , 2014 .

[23]  Bart van Arem,et al.  Recent advances and applications in the field of short-term traffic forecasting. , 1997 .

[24]  J. Pearl.  Causal inference in statistics: An overview , 2009 .

[25]  Michael J Demetsky,et al.  TRAFFIC FLOW FORECASTING: COMPARISON OF MODELING APPROACHES , 1997 .

[26]  A. Hasman,et al.  Probabilistic reasoning in intelligent systems: Networks of plausible inference , 1991 .

[27]  Alexandre d'Aspremont,et al.  Model Selection Through Sparse Max Likelihood Estimation Model Selection Through Sparse Maximum Likelihood Estimation for Multivariate Gaussian or Binary Data , 2022 .

[28]  Antony Stathopoulos,et al.  Fuzzy Modeling Approach for Combined Forecasting of Urban Traffic Flow , 2008, Comput. Aided Civ. Infrastructure Eng..

[29]  Li Li,et al.  Robust causal dependence mining in big data network and its application to traffic flow predictions , 2015 .

[30]  H. J. Van Zuylen,et al.  Accurate freeway travel time prediction with state-space neural networks under missing data , 2005 .

[31]  Eleni I. Vlahogianni,et al.  Short‐term traffic forecasting: Overview of objectives and methods , 2004 .

[32]  Gary A. Davis,et al.  Nonparametric Regression and Short‐Term Freeway Traffic Forecasting , 1991 .

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

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

[35]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

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

[37]  Yi Zhang,et al.  Trend Modeling for Traffic Time Series Analysis: An Integrated Study , 2015, IEEE Transactions on Intelligent Transportation Systems.

[38]  Eleni I. Vlahogianni,et al.  Fuzzy‐Entropy Neural Network Freeway Incident Duration Modeling with Single and Competing Uncertainties , 2013, Comput. Aided Civ. Infrastructure Eng..

[39]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[40]  Yin Wang,et al.  The retrieval of intra-day trend and its influence on traffic prediction , 2012 .

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

[42]  Stefanos D. Kollias,et al.  An adaptable neural-network model for recursive nonlinear traffic prediction and modeling of MPEG video sources , 2003, IEEE Trans. Neural Networks.

[43]  Mark Dougherty,et al.  A REVIEW OF NEURAL NETWORKS APPLIED TO TRANSPORT , 1995 .

[44]  Y. Kamarianakis,et al.  Forecasting Traffic Flow Conditions in an Urban Network: Comparison of Multivariate and Univariate Approaches , 2003 .

[45]  Henry X. Liu,et al.  Use of Local Linear Regression Model for Short-Term Traffic Forecasting , 2003 .

[46]  William H. K. Lam,et al.  Comparison of two non‐parametric models for daily traffic forecasting in Hong Kong , 2006 .

[47]  Changshui Zhang,et al.  Competitive EM algorithm for finite mixture models , 2004, Pattern Recognit..

[48]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the lasso , 2007, 0708.3517.

[49]  Li Li,et al.  Efficient missing data imputing for traffic flow by considering temporal and spatial dependence , 2013 .

[50]  Eleni I. Vlahogianni,et al.  Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach , 2005 .

[51]  Zhaohui Wu,et al.  Intelligent Transportation Systems , 2006, IEEE Pervasive Computing.

[52]  Zhong Liu,et al.  Distributed Modeling in a MapReduce Framework for Data-Driven Traffic Flow Forecasting , 2013, IEEE Transactions on Intelligent Transportation Systems.

[53]  Hojjat Adeli,et al.  Neural network model for rapid forecasting of freeway link travel time , 2003 .

[54]  Shiliang Sun,et al.  Traffic Flow Forecasting Using a Spatio-temporal Bayesian Network Predictor , 2005, ICANN.

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

[56]  Alexandre d'Aspremont,et al.  Model Selection Through Sparse Maximum Likelihood Estimation , 2007, ArXiv.

[57]  Shaun Lysen,et al.  Permuted Inclusion Criterion: A Variable Selection Technique , 2009 .

[58]  Wei Shen,et al.  Real-time road traffic forecasting using regime-switching space-time models and adaptive LASSO , 2012 .

[59]  Li Li,et al.  Missing traffic data: comparison of imputation methods , 2014 .

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

[61]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[62]  Hussein Dia,et al.  An object-oriented neural network approach to short-term traffic forecasting , 2001, Eur. J. Oper. Res..