%0 Journal Article
%T The Methods of Knowledge Database Integration Based on the Rough Set Classification and Genetic Algorithm<br>基于粗集分类和遗传算法的知识库集成方法
%A GUO Ping CHENG Dai-Jie
%A <br>郭平
%A 程代杰
%J 计算机科学
%D 2003
%I 
%X As the base of intelligent system, it is very important to guarantee the consistency and non-redundancy of knowledge in knowledge database. Since the variety of knowledge sources, it is necessary to dispose knowledge with redundancy, inclusion and even contradiction during the integration of knowledge database. This paper researches the integration method based on the multi-knowledge database. Firstly, it finds out the inconsistent knowledge sets between the knowledge databases by rough set classification and presents one method eliminating the inconsistency by test data. Then, it regards consistent knowledge sets as the initial population of genetic calculation and constructs a genetic adaptive function based on accuracy, practicability and spreadability of knowledge representation to carry on the genetic calculation. Lastly, classifying the results of genetic calculation reduces the knowledge redundancy of knowledge database. This paper also presents a framework for knowledge database integration based on the rough set classification and genetic algorithm.
%K Rough set
%K Classification
%K Genetic algorithm
%K Knowledge database
%K Integration<br>粗集
%K 知识库
%K 集成方法
%K 遗传算法
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=64A12D73428C8B8DBFB978D04DFEB3C1&aid=1E4A839B652BFF73&yid=D43C4A19B2EE3C0A&vid=340AC2BF8E7AB4FD&iid=708DD6B15D2464E8&sid=1371F55DA51B6E64&eid=BE33CC7147FEFCA4&journal_id=1002-137X&journal_name=计算机科学&referenced_num=0&reference_num=13