摘要: 提出了一种非同步时间序列特征模式提取算法,该算法在对时间序列经过符号化而获得两类字符串集合的基础上,利用遗传算法快速找到一个模式,它能充分区分两类字符串集合,可以发现所有包含此模式的时间序列。实验结果表明该算法在实践中有较好的应用前景。
关键词:
时间序列,
符号化,
部分模式匹配,
遗传算法
Abstract: This paper presents an algorithm for finding pattern of non-synchronous time series. On the basis of two sets of strings, which are produced by symbol representation of time series, using genetic algorithm, a pattern can be obtained that distinguishes sets of strings completely. By this pattern, every time series including this pattern can be found quickly. Finally the experiment shows the approach is quite promising.
中图分类号:
王刚,倪世宏,沙孟春. 基于遗传算法的非同步时间序列特征提取方法[J]. , 2005, 31(17): 165-.
WANG Gang1,NI Shihong2,SHA Mengchun1. An Algorithm for Finding Pattern of Non-synchronous Time Series Based on Genetic Algorithm[J]. , 2005, 31(17): 165-.