弱标记不完备决策系统的增量式属性约简算法  

An incremental attribute reduction algorithm for incomplete decision system with weak labeling

作　　者：程龙 钱文彬 王映龙[1] 胡剑锋[3] CHENG Long;QIAN Wenbin;WANG Yinglong;HU Jianfeng(School of Computer and Information Engineering,Jiangxi Agricultural University,Nanchang 330045,China;School of Software,Jiangxi Agricultural University,Nanchang 330045,China;Institute of Information Technology,Jiangxi University of Technology,Nanchang 330098,China)

机构地区：[1]江西农业大学计算机与信息工程学院,江西南昌330045 [2]江西农业大学软件学院,江西南昌330045 [3]江西科技学院信息技术研究所,江西南昌330098

出　　处：《智能系统学报》2020年第6期1079-1090,共12页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金项目(61966016);江西省自然科学基金项目(20192BAB207018);江西省教育厅科学技术研究项目(GJJ180200).

摘　　要：在许多现实应用领域中,由于数据标注代价昂贵,且数据往往呈现动态变化,因此存在大量弱标记的不完备数据。针对上述复杂应用场景,本文以粒计算理论为基础,从区分性视角给出不完备数据的区分对概念,同时给出属性相对重要度的度量方法,并设计面向弱标记不完备决策系统的属性约简算法。该算法能在迭代过程中不断缩减搜索空间,提高属性约简效率;并根据实例的动态变化情况,分析属性约简的动态更新机制;在此基础上,设计了半监督条件下的增量式属性约简算法。最后,通过实验验证了算法的可行性和有效性。Due to the high cost of data annotation and dynamic change of data,many practical applications have a lot of incomplete data with weak labeling.In view of the above complex scenarios,based on the theory of granular computing,the concept of discernibility pairs of incomplete data is proposed and provides a measurement method for the relative importance of attributes.The attribute reduction algorithm is designed for an incomplete decision system with weak labeling,which can reduce the search space and improve the efficiency of attribute reduction.Besides,the dynamic updating mechanism of attribute reduction is analyzed based on the dynamic change of instances.In this study,an incremental attribute reduction algorithm is designed under a semi-supervised scene,and the experimental results show the feasibility and effectiveness of the proposed algorithm.

关 键 词：属性约简 粗糙集 区分对 混合数据 增量学习 半监督学习 相对重要度 动态数据 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]