一类多粒度近似周期关联规则问题的挖掘研究
    点此下载全文
引用本文:姜华?覮,周克江.一类多粒度近似周期关联规则问题的挖掘研究[J].计算技术与自动化,2019,(1):118-121
摘要点击次数: 485
全文下载次数: 0
作者单位
姜华?覮,周克江 (湖南第一师范学院 信息科学与工程学院湖南 长沙 410205) 
中文摘要:研究一类在多粒度时间下单事件同属性不同状态之间有一定关联的近似周期规律挖掘问题。给出了多粒度近似周期关联规则模型形式化的数学定义和性质,构造了相关模型,提出了利用聚类算法挖掘周期模式并应用于股票数据进行实验,实验结果表明算法是有效的。
中文关键词:近似周期  关联规则  多粒度时间  数据挖掘
 
Study for a Kind of Approximate Periodicity Association Rules with Multi-granularity Time
Abstract:This paper discusses a problem of approximate periodicity association rules with multi-granularity time to different attribute states with the single event and the same attribute in the temporal database. Firstly,it presents some symbolic definitions for constructing multi-granularity approximate periodic association rules,and then constructs the corresponding model. Finally,the paper propo ses an algorithm based on SOM network to find approximate periodic association rules with multi-granularity. The experiments results with the stock market data demonstrate the efficiency of the proposed algorithm.
keywords:data mining  multi-granularity time  association rules  approximate periodicity
查看全文   查看/发表评论   下载pdf阅读器