摘要
针对医学领域诊断规则挖掘算法中时间和空间复杂性问题,提出一种基于邻域系统的决策表近似算法,用于医疗诊断数据挖掘预处理阶段的数据压缩.该方法以代表元素代替若干相近元素,有效地压缩了原始决策表的对象个数,同时保证决策表本身的判断能力基本不变.实例仿真表明,该算法具有比传统聚类算法更优的性能.
In order to solve the problem of time and space complexity used as the diagnosing rule in the field of medical research, a neighborhood system based approximation algorithm for decision tables which may be used to reduce the object number of a decision table in the preprocessing period of data mining is presented. When one object is selected to represent its similar objects, the similar objects are deleted from the decision table, and the object number is greatly reduced while decision ability of the table is not significantly decreased, which at the same time makes sure the decision tables′ ability of making decision isn′t changed. In a word, the experiments show that this algorithm has better function than the traditional clustering algorithm.
出处
《海军工程大学学报》
CAS
2004年第5期48-51,共4页
Journal of Naval University of Engineering
基金
国家自然科技基金资助项目(60373062)
湖南省杰出中青年专家科技基金资助项目(02JJYB012)
湖南省卫生厅科技基金资助项目(2001 Y89)
关键词
RS
领域系统
代表元素
近似算法
RS
neighborhood system
representatives element
approximation algorithm
