Neural Computing and Applications

, Volume 18, Issue 5, pp 417–422 | Cite as

Traffic congestion identification by combining PCA with higher-order Boltzmann machine

ISNN 2008

Abstract

Traffic congestion identification is a popular research topic of intelligent transport systems. Identification rate of existing methods usually cannot meet the practical requirements. To improve the identification rate and reduce the computation cost, a novel intelligent identification method is proposed. The proposed method combines principal component analysis (PCA) method with higher-order Boltzmann machine (BM). PCA is used to reduce the dimension of input feature space. It can not only reduce the computation cost but also filter noise of the source data. BM is a kind of stochastic network that can obtain the global optimum solution. Higher-order BM without hidden units can save lots of computation cost without decreasing modeling power. The trained higher-order BM is used to identify traffic state. The efficiency of the proposed method is illustrated through analyzing Jinan urban transportation data.

Keywords

Intelligent transport system (ITS) Higher-order Boltzmann machine Principal component analysis (PCA) Traffic congestion 

References

  1. 1.
    Jiang G (2004) Road traffic state detection. China Communications PressGoogle Scholar
  2. 2.
    Dudek C, Messer C, Nuckles N (1974) Incident detection on urban freeways. Transportation Research Record, Washington, DCGoogle Scholar
  3. 3.
    Persaud B, Hall F, Hall L (1990) Congestion identification aspects of the McMaster detection algorithm. Transp Res Rec 1287:167–175Google Scholar
  4. 4.
    Tauseef G Rajib C, Rami A (2004) Congestion detection and control in partial mesh using Bayesian approach. In: Student conference on engineering, sciences and technology, pp 152–164Google Scholar
  5. 5.
    Zhuang B, Yang X, Li K (2006) Criterion and detection algorithm for road traffic congestion incidents. China J Hwy Transp 19:82–86Google Scholar
  6. 6.
    Jiang G, Gang L, Wang J (2006) Traffic congestion identification method of urban expressway. J Traffic Transp Eng 6:87–91Google Scholar
  7. 7.
    Chen Y, Zhang Y (2006) Pattern discovering of regional traffic status with self-organizing maps. In: IEEE intelligent transportation systems conference. Toronto, Canada, 17–20 Sep 2006, pp 647–652Google Scholar
  8. 8.
    Graña M, d’Anjou A, Albizuri F (1997) Experiments of fast learning with high order Boltzmann machines. Appl Intell 7:287–303CrossRefGoogle Scholar
  9. 9.
    Albizuri F, d’Anjou A, Graña M, Torrealdea J, Hernandez M (1995) The high-order Boltzmann machine: learned distribution and topology. IEEE Trans Neural Netw 6:767–770. doi:10.1109/72.377984 CrossRefGoogle Scholar
  10. 10.
    Hou Z, Song K, Gupta M, Tan M (2006) Neural units with higher-order synaptic operations for robotic image processing applications. Soft Comput 11:221–228. doi:10.1007/s00500-006-0064-8 CrossRefGoogle Scholar
  11. 11.
    Simon H (2001) Neural networks: a comprehensive foundation. Prentice Hall, New YorkGoogle Scholar
  12. 12.
    Hou Z (2005) Principal component analysis (PCA) for data fusion and navigation of mobile robots. In: Kantor P et al (eds) Intelligence and security informatics. Lecture notes in computer science, vol 3495. Springer, Berlin, pp 610–611Google Scholar
  13. 13.
    Hou Z, Gupta M, Nikiforuk P, Tan M (2007) A recurrent neural network for hierarchical control of interconnected dynamic systems. IEEE Trans Neural Netw 18:466–481. doi:10.1109/TNN.2006.885040 CrossRefGoogle Scholar
  14. 14.
    Pei Y, Ma J (2003) Real-time traffic flow data screening and reconstruction. China Civ Eng J 36:78–83Google Scholar

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  1. 1.Shandong Computer Science CenterJinanChina

Personalised recommendations