基于融合云模型分析的时间序列概念划分方法  

Concept division method of time series based on cloud model analysis

作　　者：李金武[1] 王清珍[1] LI Jinwu;WANG Qingzhen(College of Information Engineering,Zhengzhou University of Science&Technology,Zhengzhou 450064,China)

机构地区：[1]郑州科技学院信息工程学院,河南郑州450064

出　　处：《河南工程学院学报（自然科学版）》2022年第3期54-60,共7页Journal of Henan University of Engineering：Natural Science Edition

基　　金：河南省科技攻关项目(142102210513);河南省高等学校重点科研项目(20B120003)。

摘　　要：为有效提取时间序列概念特征,提出了一种基于云模型的时间序列概念划分方法。该方法将时间序列转化为二维数据,综合考虑序列本身及序列变化趋势,通过二维高斯混合模型对序列高斯分布进行分解,并利用云模型变换算法实现序列概念软划分。实验结果表明,该方法能够有效地对时间序列概念进行聚类分析,为时间序列评价提供依据。In order to effectively extract the concept features of time series, this paper proposes a concept division method based on cloud model. The time series is transformed into two-dimensional data, considering the sequence itself and the change trend, the Gaussian distribution of the sequence is decomposed by two-dimensional Gaussian mixture model, and the cloud transformation algorithm is used to realize the soft partition of sequence concepts. Experimental results show that this method can effectively cluster the concepts of time series, and it provides a basis for the evaluation of time series.

关 键 词：时间序列 二维云变换 概念划分 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]