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。
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.
出处
《计算机工程》
CAS
CSCD
北大核心
2005年第17期155-156,230,共3页
Computer Engineering
关键词
时间序列
符号化
部分模式匹配
遗传算法
Time series
Symbol representation
Episode pattern matching
Genetic algorithm
