摘要
文中提出一种离散和连续混合属性的复杂信息系统增量式属性约简算法.首先,将粒计算模型中的知识粒度在混合型信息系统下进行推广,提出了邻域知识粒度,并构造出基于邻域知识粒度的非增量式属性约简算法,然后在混合型信息系统下研究了邻域知识粒度随对象增加时的增量式计算,理论证明了该计算方式的高效性,最后提出了基于邻域知识粒度的混合信息系统增量式属性约简算法.UCI数据集的实验结果表明,所提出的算法在混合型信息系统中具有很高的增量式属性约简性能.
An incremental attribute reduction algorithm for complex information systems with discrete and continuous mixed attributes was proposed. Firstly, the knowledge granulation in the granular computing model was extended under the mixed information system, the neighborhood knowledge granulation was proposed, and a non-incremental attribute reduction algorithm based on the neighborhood knowledge granulation was constructed. Then, the incremental computation of neighborhood knowledge granulation with the increase of objects was studied under the mixed information system, and the efficiency of the computation was proved theoretically. Finally, an incremental attribute reduction algorithm for mixed information systems based on neighborhood knowledge granulation was proposed. Experimental results of UCI datasets show that the proposed algorithm has high incremental attribute reduction performance in mixed information systems.
作者
段海玲
王光琼
DUAN Hailing;WANG Guangqiong(School of Economics and Management, Fuzhou University, Fuzhou 350116, Fujian,China;School of Intelligent Manufacturing, Sichuan University of Arts and Science, Dazhou 635000, Sichuan, China)
出处
《华南理工大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2019年第6期18-30,共13页
Journal of South China University of Technology(Natural Science Edition)
基金
国家自然科学基金项目(71171054)
“2019年中国物流学会、中国物流与采购联合会面上研究课题计划”面上项目(2019CSLKT3-231)~~
关键词
复杂信息系统
混合属性
属性约简
知识粒度
邻域
增量式学习
complex information system
mixed attributes
attribute reduction
knowledge granulation
neighborhood
incremental learning
