摘要
系统参数的重要性评价十分重要,本文首先讨论了通过计算特征参数的离差来分析系统参数重要性的K-W检验方法,研究了利用信息论中不确定性概念来计算熵与分类的关系的方法,以及通过计算系统参数的之间的依赖性和不可分辨性与识别系统的关系来衡量系统参数重要性的粗集理论分析方法,最后,我们给出分析属性重要性的例子,分析和比较他们之间的关系。
:It is very important to evaluate the significance of system parameters. The significance ofsystem parameters is analyzed With the method of K-W computing the mean error square of system featureparameters. A relation between classification and entropy is discussed with the conception of uncertainty ininformation science. A method of evaluating the significance of system parameters is proposed with thetheoretical aspects of rough sets by computing the dependency and the indiscernibility in knowledge base.An example of evaluating the significance of system parameters is given to make a comparison of themethods proposed.
出处
《四川轻化工学院学报》
1999年第2期10-13,共4页
Journal of Sichuan Institute of Light Industry and Chemical Technology
基金
国家自然科学基金
智能技术与系统国家重点实验室开放课题基金
关键词
系统参数
模式识别
不确定性
粗集
system parablers
pattern recognition: uncertainty: rough sets