期刊文献+

几种分形参数估计方法的性能分析和比较 被引量:9

A fractal based analysis of time series data and feature extration
下载PDF
导出
摘要 讨论了一维时间序列的分形分析和参数提取,论述了分维数的估计,介绍了几种常用方法,并提出一种基于有限长度信号方差的估计方法.用实验分析了这些计算方法的准确性、平稳性、计算复杂度、受噪声和信号长度的影响等方面的性能,得到一些有意义的结论.实验结果表明。 We deal with the problem of the fractal based analysis of and feature extraction from real valued topological “one dimensional” time series data, with emphasis on the estimation of the fractal dimension. Several common methods are introduced and a new algorithm for measuring the fractal dimension is proposed. Experiments are used to analyse their performance such as estimation accuracy, stability, computation complexity and the effects of added noise and length of series on all these methods, with some useful conclusions reached, which show the proposed method is efficient and somewhat superior.
出处 《西安电子科技大学学报》 EI CAS CSCD 北大核心 1997年第2期172-179,共8页 Journal of Xidian University
基金 国防预研基金和博士点基金
关键词 分形 分维 分数布朗运动 序列分析 信号分析 fractal fractal dimension fractional Brownian motion time series analysis
  • 引文网络
  • 相关文献

参考文献1

  • 1李后强,分形理论及其在分子科学中的应用,1993年

同被引文献60

引证文献9

二级引证文献29

;
使用帮助 返回顶部