基于信息熵的粗糙集属性约简及其应用  

Attribute reduction in rough set based on information entropy and it’s application

作　　者：丁守祯[1] 桑琳[1] 朱全英[1] 狄海涛[2] 

机构地区：[1]大连海事大学数学系,辽宁大连116026 [2]大连海事大学轮机工程学院,辽宁大连116026

出　　处：《计算机工程与应用》2007年第35期245-248,共4页Computer Engineering and Applications

基　　金：国家自然科学基金( the National Natural Science Foundation of China under Grant No.50575026);辽宁省教育厅资助项目( No.2005063)

摘　　要：粗集约简对噪声非常敏感,因此寻求噪声干扰下,属性间的准确关系和不确定性关系的表达显得十分重要。将粗糙集理论与信息论理论结合起来,发挥各自优势,取长补短,提出了一种改进的属性约简算法,且在此基础上进行了值约简并应用于超大型船舶的旋回性分析。给出了各因素之间的依赖关系,增比特征,及规则分析。取得了很好效果,对船舶操纵和技术研究有良好的实用价值。Attribute reduction in rough set theory is very sensitive to dates of noises.So it＇s very significant to depict the extract relationship and uncertain relationship among attributes under the condition of noises interference.Rough set theory and information theory are combined in this paper with advantages are exerted and disadvantages are limited between each other.Then,a new attribute algorithm is presented and applied in gyration analyse of the biggest shipping.At the same time,the relationship rely on each other and the characteristics of increase or decrease are depicted,besides,some sorts of rules are obtained.It is testified that the method presented here are effective and practicality to manipulate and technology research of shipping.

关 键 词：粗糙集 属性约简 信息熵 粗糙逻辑 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP274[自动化与计算机技术—控制科学与工程]