基于时间序列数据流的挖掘频繁串行情节的研究  

Mining Frequent Episodes Based on Time Serial Data Stream

作　　者：周则顺 

机构地区：[1]湖北省高等学校招生委员会办公室,湖北武汉430077

出　　处：《武汉理工大学学报（信息与管理工程版）》2006年第5期12-16,共5页Journal of Wuhan University of Technology：Information & Management Engineering

摘　　要：针对在时间序列数据流中挖掘频繁串行情节的问题,提出了一种具有可持续挖掘的方法—TFSE(Tim e-tab le-joined Frequent Serial Ep isodes)。该方法引入了情节时间表和再次挖掘的概念,一个情节模式对应一个情节时间表,通过在情节时间表之间做数据库联接操作,生成相应新的情节时间表。情节时间表记录个数即是该情节的支持数。Aiming at mining frequent episodes in time serial data stream, an approach of Time -table -joined Frequent Serial Episodes （TFSE） is presented, which includes the conception of the episode - time - table and the re - mining. An Episode - time - table corresponds to an episode pattern and a new Episode - time - table is generated by the joining databases. The amount of records in the Episode - time - table is equal to the number of episodes occurring in the time series.

关 键 词：数据挖掘 时间序列 情节时间表 频繁串行情节 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]