Traffic Flow Prediction Using MI Algorithm and Considering Noisy and Data Loss Conditions: An Application to Minnesota Traffic Flow Prediction

  • Seyed Hadi Hosseini Department of Electrical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
  • Behzad Moshiri Control and Intelligent Processing Center of Excellence, School of ECE, University of Tehran, Tehran, Iran.
  • Ashkan Rahimi-Kian Control and Intelligent Processing Center of Excellence, School of ECE, University of Tehran, Tehran, Iran.
  • Babak Nadjar Araabi Control and Intelligent Processing Center of Excellence, School of ECE, University of Tehran, Tehran, Iran.
Keywords: ITS, mutual information, traffic flow forecasting, noisy data, data loss,

Abstract

Traffic flow forecasting is useful for controlling traffic flow, traffic lights, and travel times. This study uses a multi-layer perceptron neural network and the mutual information (MI) technique to forecast traffic flow and compares the prediction results with conventional traffic flow forecasting methods. The MI method is used to calculate the interdependency of historical traffic data and future traffic flow. In numerical case studies, the proposed traffic flow forecasting method was tested against data loss, changes in weather conditions, traffic congestion, and accidents. The outcomes were highly acceptable for all cases and showed the robustness of the proposed flow forecasting method.

References

Castro-Neto M, Jeong YS, Jeong MK, Han LD. Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions. Expert Sys with Appl. 2009 Apr;36(3):6164-6173.

Zhang Y. How to provide accurate and robust traffic forecasts practically?. Intel Transportation Sys. 2012 Mar;8:189-206.

Stathopoulos A, Dimitriou L, Tsekeris T. Fuzzy modeling approach for combined forecasting of urban traffic flow. Comp Aid Civil and Infra Eng. 2008 Oct;23(7):521-535.

Jiang X, Adeli H. Dynamic wavelet neural network model for traffic flow forecasting. J Transportation Eng. 2005 Oct;131(10):771-779.

Sun H, Liu HX, Xiao H, Ran B. Short-term traffic forecasting using the local linear regression model. Center for Traffic Simulation Studies [Internet]. UC Irvine: Center for Traffic Simulation Studies. 2002; Available from: http://escholarship.org/uc/item/540301xx

Smith BL, Williams BM, Oswald RK. Comparison of parametric and nonparametric models for traffic flow forecasting. J Transportation Res Part C. 2002 Aug;10(4):303-321.

Ramezani A, Moshiri B, Rahimi-Kian A, Araabi BN, Abdulhai B. Distributed maximum likelihood estimation for flow and speed density prediction in distributed traffic detectors with Gaussian mixture model assumption. IET Intel Transportation Sys. 2012 Jun;6(2):215-222.

Zhang Y, Ye Z. Short-Term Traffic Flow Forecasting Using Fuzzy Logic System Methods. J Intel Transportation Sys. 2008 Jul;12(3):102-112.

Chang H, Lee Y, Yoon B, Baek S. Dynamic near-term traffic flow prediction: System-oriented approach based on past experiences. IET Intel Transportation Sys. 2012 Sep;6(3):292-305.

Prochazka A. Neural networks and seasonal time-series prediction. 5th International Conference on Artificial Neural Networks. 7-9 July 1997, Cambridge, UK; 1997. p. 36-41.

Chandra SR, Al-Deek H. Predictions of freeway traffic speeds and volumes using vector autoregressive models. J Intel Transportation Sys. 2009 Apr;13(2):53-72.

Williams BM. Multivariate vehicular traffic flow prediction: An evaluation of ARIMAX modeling. Transportation Res Board. 2002 Mar; 00824511:194-200.

Ledoux C. An urban traffic control system integrating neural networks. 8th International Conference on Road Traffic Monitoring and Control. 23-25 April 1996, London, UK; 1996. p. 197-201.

Zhang Y, Ye Z. Short-term traffic flow forecasting using fuzzy logic system methods. J Intel Transportation Sys. 2008 Aug;12(3):102-112.

Lim S, Lee C. Data fusion algorithm improves travel time predictions. IET Intel Transportation Sys. 2011 Dec;5(4):302-309.

Yu D, An S, Hu Q. Fuzzy mutual information based min-redundancy and max-relevance heterogeneous feature selection. Int J Comp Intel Sys. 2011 Mar;4(4):619-633.

Wei D, Liu H. An adaptive-margin support vector regression for short-term traffic flow forecast. J Intel Transportation Sys. 2013 Nov;17(4):317-327.

Ghosh B, Basu B, O’Mahony M. Bayesian time-series model for short-term traffic flow forecasting. J Transportation Eng. 2007 Mar;133(3):180-189.

Xie Y, Zhang Y. A wavelet network model for short-term traffic volume forecasting. J Intel Transportation Sys. 2007 Jan;10(3):141-150.

Abdulhai B, Porwal H, Recker W. Short-term traffic flow prediction using neuro-genetic algorithms. J Intel Transportation Sys. 2002 Jan;7:3-41.

Zeng D, Xu J, Gu J, Liu L, Xu G. Short term traffic flow prediction using hybrid ARIMA and ANN models. Workshop on Power Electronics and Intel Transportation Sys. 2-3 August 2008, Guangzhou, China; 2008. p. 621-625.

Messai N, Thomas P, Lefebvre D, El-Moudni A. A Neural Network Approach for Freeway Traffic Flow Prediction. International Conference on Control App. 18-20 September 2002, Glasgow, UK; 2002. p. 984-989.

Yuan J, Mills K. A Cross-Correlation Based Method for Spatial-Temporal Traffic Analysis. J Perform Eval. 2005 Jul;61(2-3):163-180.

Williams JW, Li Y. Estimation of mutual information: A survey. 4th International Conference on Rough Sets and Knowledge Technology. 14-16 July 2009, Gold Coast, Australia; 2009. p. 389-396.

Kraskov A, Stögbauer H, Grassberger P. Estimating Mutual Information. Physical Rev E. 2004 Jun;69(066138):1-16.

Stögbauer H, Kraskov A, Astakhov SA, Grassberger P. Least Dependent Component Analysis Based on Mutual Information. Physical Rev E. 2004 Sep;70(066123):1-18.

Dasarathy BV. Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques. Mc Graw-Hill: Computer Science Series, IEEE Computer Society Press: Las Alamitos, California; 1991.

Battiti R. Using mutual information for selecting features in supervised neural net learning. IEEE Trans Neural Net. 1994 Jul;5(4):537-550.

Deng K. OMEGA: On-line Memory-based General Purpose System Classifier [dissertation]. Carnegie Mellon University; Pittsburgh (PA): University of Pittsburgh; 1998.

[Cited 2013 Jun 30]. Available from: http://www.d.umn.edu/tdrl/traffic

[Cited 2014 Jul 10]. Available from: http://weatherspark.com/history/30956/2012/Minneapolis-Minnesota-United-States.

Tan MC, Wong SC, Xu JM, Guan ZR, Zhang P. An Aggregation Approach to Short-Term Traffic Flow Prediction. IEEE Trans Intel Transportation Sys. 2009 Mar;10(1):60-69.

Published
2014-10-31
How to Cite
1.
Hosseini SH, Moshiri B, Rahimi-Kian A, Araabi BN. Traffic Flow Prediction Using MI Algorithm and Considering Noisy and Data Loss Conditions: An Application to Minnesota Traffic Flow Prediction. PROMET [Internet]. 2014Oct.31 [cited 2019Aug.23];26(5):393-0. Available from: http://traffic.fpz.hr/index.php/PROMTT/article/view/1429
Section
Articles