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