基于J2EE平台应用时序挖掘算法对纺织品出口风险预测的研究  

J2EE Based Platform of Time Series Mining Algorithm Forecast the Risks of Textile' s Exports

作　　者：谢挺[1] 楼巍[1] 

机构地区：[1]上海大学机电工程与自动化学院,上海200072

出　　处：《微计算机信息》2006年第09X期254-256,共3页Control & Automation

摘　　要：贸易数据是按时间记录下的、不断更新中的海量数据。首先引入时间序列模式的概念,分析了时间序列的本质问题;其次改进了AprioriAll算法挖掘贸易序列数据库的有用序列模式;然后使用离散傅里叶变换子序列相似性查找的方法,将现有序列与挖掘到的感兴趣的序列模式进行子序列匹配,得到有用的知识;最后结合实际情况,合理搭建系统平台,将改进的算法应用在该平台之下得到满意的效果。It is well known that the commerce data are collected by time sequence and the commerce datebases have a great many records which update incessantly. Firstly, in this paper, the concept Time Series is introduced and its intrinsic property is discussed. Secondly, a novel data mining algorithm base on AprioriAll is developed to find useful sequential pattern in commerce databases, then use discrete Fourier transform analysis the similarity sub-series searching method. Finally, the system platform is developed and obtain a satisfied results.

关 键 词：数据挖掘 序列模式 时间序列 相似性查找 HIBERNATE 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]