基于优势关系粗糙集的地震数据约简和规则提取  

Attribute Reduction and Rule Extraction for Earthquake Data Based on Dominance Relation Rough Set

作　　者：吴绍春[1] 郑宇[1] 吴耿锋[1] 朱冰冰[1] 

机构地区：[1]上海大学计算机工程与科学学院,上海200072

出　　处：《上海大学学报（自然科学版）》2007年第5期566-570,共5页Journal of Shanghai University:Natural Science Edition

基　　金：国家地震科学联合基金资助项目(104090);上海市自然科学基金资助项目(03ZR14038)

摘　　要：针对现有的基于不可分辨关系的数据约简算法在地震数据处理中存在的缺点,提出一个新的优势区分矩阵的定义,并在此基础上给出相应的具有更好约简效率的数据约简算法和规则提取算法.在运用该算法对全国小震目录数据进行的实验中,从上海市地震局提供的44 381条样本数据中挖掘出272条确定性规则,取得了有实际意义的结果.After discussing the classical rough set theory based on indiscemibility relation and its reduction algorithms on earthquake data, we present a new definition of dominance discemibility matrix by taking advantage of the unique characteristic of the extended model. The corresponding reduction and rule extraction algorithms are then given accordingly to enhance efficiency in seeking the reduction to some extent, We use the rough set theory based on dominance relation to get 272 rules with realistic meaning from 44 381 items in a small set of earthquake data of China. 　

关 键 词：地震数据 粗糙集 优势关系 知识约简 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]