Advertisement

Busy Hour Traffic of Wireless Mobile Communication Forecasting Based on Hidden Markov Model

  • DongLing Zhang
  • ZhenHong Jia
  • XiZhong Qin
  • DianJun Li
  • ChaoBen Du
  • Li Chen
  • Lei Sheng
  • Hong Li
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 169)

Abstract

In order to forecast mobile communication traffic quickly and accurately, Hidden Markov Models (HMM) is used to forecast busy hour traffic of wireless mobile communication forecasting in this paper. Because of the model having rigorous mathematical structure, reliable computing performance and the characteristics of describing the event, HMM becomes the ideal model for describing the traffic sequence. The experimental results shows that HMM model have higher precision and better stability compared with the method of SVM with DE-strategy in the area of forecasting mobile communication traffic.

Keywords

Hidden Markov Models busy traffic forecasting 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yan, X., Jia, Z., Qin, X.: Traffic Forecasting based on VMPSO—BP Neural Network Algorithm. Comunications Technology 44(01), 96–98 (2011) (in Chinese)Google Scholar
  2. 2.
    Han, R., Jia, Z., Qin, X.: Application of Support Vector Machine to Mobile Communications in Telephone Traffic Load of Monthly Busy Hour Prediction. In: 2009 Fifth International Conference on Natural Computation, pp. 349–352 (2009)Google Scholar
  3. 3.
    Xie, H., Anreae, P., Zhang, M., Warren, P.: Learning Models for English Speech Recognition. In: 27th Conference on Australasian Computer Science, pp. 323–329 (2004)Google Scholar
  4. 4.
    Cheung, L.W.-K.: Use of runs statistics for pattern recognition in genomic DNA sequences. Journal of Computational Biology 11, 107–124 (2004)CrossRefGoogle Scholar
  5. 5.
    Park, S.-H., Lee, J.-H., Song, J.-W., Park, T.-S.: Forecasting Change Directions for Financial Time Series Using Hidden Markov Model. In: Wen, P., Li, Y., Polkowski, L., Yao, Y., Tsumoto, S., Wang, G. (eds.) RSKT 2009. LNCS, vol. 5589, pp. 184–191. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Li, S.T., Cheng, Y.C.: A Stochastic HMM-Based Forecasting Model for Fuzzy Time Series. IEEE Transactions on Systems, MAN, and Cybernetics—Part B: Cybernetics 40(05), 1255–1266 (2010)CrossRefGoogle Scholar
  7. 7.
    Hassan, M.R., Nath, B.: Stock market forecasting using Hidden Markov Model: a new approach. In: 05th International Conference on Intelligent Systems Design and Applications, pp. 192–196 (2005)Google Scholar
  8. 8.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  9. 9.
    Longa, Z., Younan, N.H.: Statistical image modeling in the contour let domain using contextual hidden Markov models. Signal Processing 89(5), 946–951 (2009)CrossRefGoogle Scholar
  10. 10.
    Han, R., Jia, Z., Qin, X.: Telephone Traffic Load Prediction Based on SVR with DE-strategy. Computer Engineering 37(2), 178–182 (2011) (in Chinese)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  • DongLing Zhang
    • 1
  • ZhenHong Jia
    • 1
  • XiZhong Qin
    • 1
  • DianJun Li
    • 1
  • ChaoBen Du
    • 1
  • Li Chen
    • 2
  • Lei Sheng
    • 2
  • Hong Li
    • 2
  1. 1.College of Information Science & EngineeringXinjiang UniversityUrumqiP.R. China
  2. 2.China Mobile Group Xinjiang Company LimitedUrumqiP.R. China

Personalised recommendations