摘要
基于差别矩阵的约简算法简单、计算量小,但是传统的差别矩阵不能处理噪声数据。为提高差别矩阵的适用范围,提出一种能够容忍数据中包含噪声的变精度差别矩阵,并给出改进的基于条件属性偏序关系的约简算法。最后,将这一方法用于对多类图像的分类过程中,将分类结果与BP网络的分类结果和基于传统Skowron差别矩阵方法的分类结果相比较表明这种分类方法具有较好的结果。
The reduction algorithm based on discernibility matrix is simple and easy,but it cant deal with noisy data. To make discernibility matrix more useful, we propose a new version of discernibility matrix, so called variable precision discernibility matrix, which can tolerate the noise of information, in addition, a reduction algorithm is also presented based on the partial order relation of the conditional attribute and used to do image classification. Compared with traditional BP network and Skowron discernibility matrix based method, the result will be much better.
出处
《计算机科学》
CSCD
北大核心
2004年第3期142-144,共3页
Computer Science
基金
国防十五重点预研项目(102010302)
研究生创新基金(Z20030046)
校青年基金(521020101-0900-020101)
关键词
神经网络
变精度粗集
分类
约简算法
决策属性
Variable precision rough set, Discernibility matrix, Images classification
