基于分形理论的交通事故分析
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
以某市交通事故统计资料为例,首先采用功率谱分析方法论证了分形理论用于交通事故分析的可行性,计算结果表明在统计意义上,该市交通事故时间序列具有自仿射性。接着利用分形的自相似性与标度不变性将内区间的分形特性进行延拓,并由此构造了具有外推功能的分形插值算法,实现交通事故预测。该算法利用内区间的迭代函数系和吸引子由特定初始点进行搜索,通过迭代使得到的点集与吸引子的均方偏差最小,从而获得需要外推点的函数值作为预测值。最后对交通事故时间序列进行R/S分析,进一步验证了预测结果的合理性,结果表明该市未来几年交通事故仍有增长趋势,应继续加强交通管理。
Taking statistic data of traffic accidents of a city as an example,the feasibility to analyze traffic accident using fractal theory was demonstrated firstly by power spectrum analysis.The calculation result shows that in the sense of statistics,time series of annual distribution of traffic accidents has certain self-affinity.Then the fractal property of inner interval was extended outwards by self-similarity and scale invariance of fractal,and on this basis a fractal extrapolation algorithm was proposed to realize the prediction of traffic accidents.By this algorithm the search was performed from a certain initial point by use of iterated function system and attractor of inner interval.When the mean square deviation between point set obtained by iteration and attractor become the minimum,the prediction value can be used as the function value of the point to be extrapolated.Finally,the R/S fractal analysis of time series of traffic accidents further shows that the forecasting value is reasonable.Case study results show that there will still be growth trend in the next few years and traffic management should be continued to strengthen.
引文
[1]李相勇,张南,蒋葛夫.道路交通事故灰色马尔可夫预测模型[J].公路交通科技,2003,20(4):98-100.LI Xiang-yong,ZHANG Nan,JIANG Ge-fu.Grey-markovModel for Forecasting Road Accidents[J].Journal of Highwayand Transportation Research and Development,2003,20(4):98-100.
    [2]李娟,邵春福.基于BP神经网络的交通事故预测模型[J].交通与计算机,2006,24(2):34-37.LI Juan,SHAO Chun-fu.The Forecasting Model for TrafficAccident Based on BP Neural Network[J].Computer andCommunications,2006,24(2):34-37.
    [3]曾文曲,王向阳.分形理论与分形的计算机模拟[M].沈阳:东北大学出版社,2001.ZENG Wen-qu,WANG Xiang-yang.Fractal Theory and Com-puter Simulation of Fractal[M].Shenyang:North East Uni-versity Press,2001.
    [4]李红启,刘凯.基于分形理论的铁路货运量分析[J].铁道学报,2003,25(3):19-23.LI Hong-qi,LIU Kai.Analysis of Railway Freight Volume Basedon Fractal Theory[J].Journal of the China Railway Society,2003,25(3):19-23.
    [5]徐学明,王丽,荣建.功率谱在交通流混沌现象研究中的应用[J].公路交通科技,2006,23(3):125-127.XU Xue-ming,WANG Li,RONG Jian.Application of PowerSpectrum in Research of Chaos in Traffic Flow[J].Journal ofHighway and Transportation Research and Development,2006,23(3):125-127.
    [6]陈,陈凌.分形几何学[M].北京:地震出版社,1998.CHEN Yu,CHEN Ling.Fractal Geometry[M].Beijing:Earth-quake Press,1998.
    [7]姚辉学,卢章平.随机工程曲线的分形插值方法研究[J].江苏理工大学学报(自然科学版),1999,20(4):76-80.YAO Hui-xue,LU Zhang-ping.Study on Linear Fractal Inter-polation for Random Engineering Curve[J].Journal of Jiang-su University of Science and Technology(Natural Science),1999,20(4):76-80.
    [8]薛万磊,于继来.分形外推插值算法在电力负荷预测中的应用[J].电网技术,2006,30(13):49-54.XUE Wan-lei,YU Ji-lai.Application of Fractal ExtrapolationAlgorithm in Load Forecasting[J].Power System Technology,2006,30(13):49-54.
    [9]DAVID S M,MOSON H H.Using Iterated Function Systems toModel Discrete Sequences[J].IEEE Trans on Signal Process-ing,1992,40(7):1 724-1 734.
    [10]徐水太,饶运章.基于R/S分析矿山铜污染分形预测[J].矿业安全与环保,2006,33(5):72-73.XU Shui-tai,RAO Yun-zhang.Fractal Forecast of Mine Cu-prum Pollution Based on R/S Analysis[J].Mining Safety andEnvironmental Protection,2006,33(5):72-73.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心