• DocumentCode
    1848827
  • Title

    Prediction of Vessel Traffic Accident Based on Chaotic Theory

  • Author

    Zhou, Jinyong ; Gao, Lan ; Hua, Qing

  • Author_Institution
    Wuhan Univ. of Technol., Wuhan
  • fYear
    2008
  • fDate
    18-21 Nov. 2008
  • Firstpage
    2727
  • Lastpage
    2731
  • Abstract
    It is well known that the vessel traffic accident is a quite complex event induced by many kinds of factors, which can be concluded as persons, ships, and environment. As a result of interaction and intercoupling of these factors, the whole system has highly nonlinear characteristics. Due to the limitation of traditional linear prediction, it is significant to put the chaotic theory into the vessel traffic accident prediction. As a new attempt this paper at first analyzes chaotic characteristics appeared in vessel traffic accident, and then presents the chaotic adaptive prediction model based on wavelet de-noising. In theory this model is suitable for the vessel traffic accident prediction whose history record contains only small data sets but with much noise. In practice the following simulation results on MATLAB software platform show the effectiveness of the model described which has high prediction accuracy and can meet the actual need.
  • Keywords
    chaos; marine accidents; prediction theory; ships; traffic engineering computing; wavelet transforms; MATLAB software; chaotic adaptive prediction model; chaotic theory; vessel traffic accident prediction; wavelet denoising; Accuracy; Chaos; History; MATLAB; Marine vehicles; Mathematical model; Noise reduction; Predictive models; Road accidents; Wavelet analysis; Chaos; chaotic adaptive prediction; phase space reconstruction; wavelet de-noising;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Young Computer Scientists, 2008. ICYCS 2008. The 9th International Conference for
  • Conference_Location
    Hunan
  • Print_ISBN
    978-0-7695-3398-8
  • Electronic_ISBN
    978-0-7695-3398-8
  • Type

    conf

  • DOI
    10.1109/ICYCS.2008.221
  • Filename
    4709411