基于信息颗粒和模糊聚类的时间序列分割  

Time-series Segmentation Based on Fuzzy Clustering Algorithm and Information Granules

作　　者：王立柱[1,2] 刘晓东[2] 

机构地区：[1]沈阳师范大学数学与系统科学学院,辽宁沈阳110034 [2]大连理工大学电子信息与电气工程学部,辽宁大连116024

出　　处：《模糊系统与数学》2015年第1期175-182,共8页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(61175041)

摘　　要：提出了基于信息颗粒和模糊聚类的时间序列分割方法。首先,使用Gath-Geva模糊聚类得到一个带有时间域信息的模糊分割;然后,在此基础上采用信息颗粒使得时间序列的分割具有数据上的同质性;最后,得到既有时间信息又有同质性的时间序列分割。将台湾证券交易所市值加权指数及某地区电力需求量序列作为实验数据,实验结果表明该方法是可行有效的。A method of time series segmentation was proposed based on fuzzy clustering algorithm. First, in our method, temporal information was involved in segmentation through Gath-Geva fuzzy clustering algorithm, and we obtain a fuzzy partition of time series with temporal information. Then, we find homogeneous segments from given time-series by means of information granules. At last, the effective segmentation was formed with consideration of time domain information and homogeneous character. To verify the effectiveness of our approach, we apply the proposed method to segment the Taiwan Stock Exchange Capitalization Weighted Stock Index. Empirical results show that variation trend and homogeneous character can be detected from the segmentation.

关 键 词：时间序列分割 模糊聚类 信息颗粒 粒子群算法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]