Weighted rough set model

被引：0

作者：

Ma, Tinghuai ^{[1
]}

Tang, Meili ^{[2
]}

机构：

[1] Nanjing Univ Info & Sci Tech, Dept Comp Sci, Nanjing, Peoples R China

[2] Nanjing Univ Info & Sci Tech, Publ Adm Dept, Nanjing, Peoples R China

来源：

ISDA 2006: SIXTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, VOL 1 | 2006年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Equal set is the most important concept in rough set. In classic rough set model, the equality is strong, must be very precise. But strong equality cause inapplicable due to data noise. Variable precision rough set model solve the data noise by introducing an error-tolerated factor. But there are no weighted factors in knowledge system. Especially, after data cleaning, rules those have same form will be unite to one rule. But objects have different importance is more close to actually application. In this paper, weighted rough set (WRS) model is provided. WRS is based on variable precision rough set (VPRS) model. This model not only considers the noise tolerant capability, but also considers the objects' importance. In weighted rough set model, some basic concepts are redefined Also, reduction definition is provided. At last, from the experiments, weighted rough set model's characters are got.

引用

页码：481 / 485

页数：5