数据挖掘综述  

Survey of Data Mining

作　　者：王光宏[1] 蒋平[1] 

机构地区：[1]同济大学信息与控制工程系,上海200092

出　　处：《同济大学学报（自然科学版）》2004年第2期246-252,共7页Journal of Tongji University:Natural Science

基　　金：国家自然科学基金资助项目(60175028)

摘　　要：从人工智能、统计分析和数据库技术3个方面对数据挖掘技术进行了总结;从模式识别的角度讨论了数据挖掘技术的主要任务,包括分类、聚类、回归、关联、序列和偏差6种模式的识别.详细介绍了数据挖掘技术的常用方法,包括模糊理论、粗糙集理论、云理论、证据理论、人工神经网络、遗传算法以及归纳学习.列举了当前数据挖掘技术的实际应用场合,并指出其今后的发展趋势以及急需关注的问题.This paper provides a survey for data mining,which combines artificial intelligence,statistical analysis,and database management system attempting to extract knowledge from databases. From the point of view of pattern recognition, different data mining tasks are discussed, including classification, clustering, regression, association, sequential and deviation pattern recognition. Mostly used methods are introduced in detail, including fuzzy method, rough sets theory, cloud theory, evidence theory, artificial neural networks, genetic algorithms and induction learning. Applications,trends and attentions of data mining are also mentioned finally.

关 键 词：数据挖掘 数据库中知识发现 人工智能 模式 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]