基于模糊粗糙集的快速降维方法及其在课程考核管理中的应用  

A Quick Dimension Reduction Method Based on Fuzzy Rough Set and Its Application to Management of Course Examination

作　　者：窦慧莉 宋晶晶 DOU Huili;SONG Jingjing(School of Computer,Jiangsu University of Science and Technology,Zhenjiang 212100,China)

机构地区：[1]江苏科技大学计算机学院,江苏镇江212100

出　　处：《山西大学学报（自然科学版）》2022年第5期1229-1237,共9页Journal of Shanxi University(Natural Science Edition)

基　　金：国家自然科学基金(61906078);江苏省研究生教育教学改革课题(JGKT22_C092);2022年江苏科技大学教育教学改革研究课题。

摘　　要：为了加快属性降维的速度,提出一种基于模糊粗糙集模型的属性约简搜索策略。首先,从数据的属性层面出发,通过计算不同属性间的相似度,将属性分组,以减少搜索在执行过程中需要遍历的属性个数,进而,利用某高校课程考核管理工作中收集的真实数据,说明了算法在逻辑上的合理性。最后,通过公开数据集上的对比分析实验,验证了算法在性能上的优越性。实例分析和实验结果充分说明,所提算法具有较强的实用性和可操作性,且在不降低分类性能甚至提高分类性能的前提下,展现出显著的时间优势。To accelerate the process of dimension reduction in data, a new searching strategy for attribute reduction is proposed based on fuzzy rough set. Firstly, the similarities among attributes are calculated from the perspective of attribute in data. Attributes are then divided into different groups to reduce the number of attributes which should be scanned in the process of searching. Furthermore, the algorithm is validated from the perspective of logic by analyzing the real data of a task of management of course examination in a university. Finally, the superiority of algorithm is also demonstrated by performing comparative experiments over open data sets. Both the case study and experimental analyses show that the proposed algorithm possesses strong practicability and maneuverability.

关 键 词：模糊粗糙集 属性约简 属性相似度 课程考核 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]