Traffic Flow Estimation System using a Hybrid Approach

  • Aung, Swe Sw (Information Engineering Department, University of the Ryukyus) ;
  • Nagayama, Itaru (Information Engineering Department, University of the Ryukyus) ;
  • Tamaki, Shiro (Information Engineering Department, University of the Ryukyus)
  • Received : 2017.02.07
  • Accepted : 2017.05.31
  • Published : 2017.08.30


Nowadays, as traffic jams are a daily elementary problem in both developed and developing countries, systems to monitor, predict, and detect traffic conditions are playing an important role in research fields. Comparing them, researchers have been trying to solve problems by applying many kinds of technologies, especially roadside sensors, which still have some issues, and for that reason, any one particular method by itself could not generate sufficient traffic prediction results. However, these sensors have some issues that are not useful for research. Therefore, it may not be best to use them as stand-alone methods for a traffic prediction system. On that note, this paper mainly focuses on predicting traffic conditions based on a hybrid prediction approach, which stands on accuracy comparison of three prediction models: multinomial logistic regression, decision trees, and support vector machine (SVM) classifiers. This is aimed at selecting the most suitable approach by means of integrating proficiencies from these approaches. It was also experimentally confirmed, with test cases and simulations that showed the performance of this hybrid method is more effective than individual methods.


  1. D. osenbaum, J. Leitloff, F. Kurz, O. Meynberg, and T. Reize, "Real-Time Image Processing for Road Traffic Data Extraction from Aerial Images", Vienna, Austria, July 5-7, 2010, IAPRS, Vol.XXXVIII, Part 7B.
  2. P.Niksaz, "Automatic Traffic Estimation Using Image Processing", International Journal of Signal Processing, Image Processing and Pattern Recognition, vol.5, No. 4, December, 2012.
  3. S.M. Hashemi, M.Almasi, R.Ebrazi, M.Jahanshahi, "Predicting the Next State of Traffic by Data Mining Classification Techniques", International Journal of Smart Electronical Engineering. Vol.1,No.3,2012, pp.181:193.
  4. X.Lu, T.Izumi, L.Teng and L.Wang, "Particle Filter Vehicle Tracking Based on SURF on SURF Feature Matching", IEEJ Journal of Industry Applications, Vol.3 No.2 pp. 182-191, May 15, 2013.
  5. D.Gao, J.Zhou, and L.Xin, "SVM-based Detection of Moving Vehicles for Automatic Traffic Monitoring", IEEE Intelligent Transportation Systems Conference Proceedings-Oakland (CA) , Page(s):745 - 749, August 25-29, 2001.
  6. J.Wang, W.Deng, and Y.Guo, Nextrans Center, Purdue University, West Lafayette, IN 47906, USA, "New Bayesian combination method for short-term traffic flow forecasting", Transportation Research Part C 43 (2014) 79-94.
  7. V.Petridis et al., "A Bayesian Models Combination Method for Time Series Prediction ", Journal of Intelligent and Robotic Systems, Volume 31, Issue 1, pp 69-89, May 2001.
  8. Y.Qi and S.Ishak, "A Hidden Markov Model for short term prediction of traffic conditions of freeways", Transportation Research Part C 43 (2014) 95-111.
  9. F.G. Habtemichael and M.Cetin, "Short-term traffic flow rate forecasting based on identifying similar traffic patterns", Transportation Research Part C 66 (2016) 61-78.
  10. R. Sarin, E. Horvittz, J. Apacible and L. Liao., "Prediction, expectation, and surprise: Methods, designs, and study of a deployed traffic forecasting service", In Twenty-First Conference on Uncertainty in Artificial Intelligence, UAI-2005, UAI-P-2005- PG-275-283.
  11. E. Bolshinsky and R. Freidman, "Traffic Flow Forecast Survey", Technion-Computer Science Department- Technical Report CS-2012-06-2012, June 3, 2012.
  12. S.S. A, S.Tamaki, I.Nagayama, "Advanced Traffic Prediction System by Socio-Technical Sensor Fusion using Machine Learning", International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSSC-2016), pp. 709 - 712, July 13, 2016.
  13. L.J. Cao and F.E.H. Tay, Department of Mechanical Engineering, the national University of Singapore, "Support Vector Machine with Adaptive Parameters in Financial Time Series Forecasting", IEEE Transactions on Neural Networks, Vol.14, No.6, November 2003.
  14. M.C.Neto, Y.S.Jeong, M.K.Jeong, and L.D.Han,Department of Civil and Environmental Engineering, University of Tennessee, USA, "Online- SVR for short-term traffic flow prediction under typical and atypical traffic conditions", Expert System with Applications Journal, Vol 36, Issue 3, Pages 6164-6173, April 2009.
  15. Y.Wang, Center for Outcomes Research and Evaluation, Yale University and Yale New Haven Health System, USA, "A multinomial logistic regression modeling approach for anomaly intrusion detection", Computer & Security Journal, Volume 24, Issue 8, Pages 662-674, 13 May 2005.