基于案例库维护的案例推理分类技术  

Case-based reasoning classification based on case base maintenance

作　　者：倪志伟[1] 倪丽萍[1] 叶红云[1] 吴昊[1] 

机构地区：[1]合肥工业大学管理学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2007年第12期1651-1655,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金重点资助项目(70631003);安徽省教育厅科研资助项目(2006sk010)

摘　　要：分类是数据处理和数据挖掘的重要任务之一,文章在建立案例推理分类器之前,先利用相似粗糙集进行案例属性的约简,再利用基于案例分类的删除技术进行案例库的维护操作;不仅减少案例的存储空间,也大大提高分类的精确度;实验结果表明,相比传统的案例推理分类器和神经网络分类器,该分类器在分类精度和速度上都有一定的优势。Classification is one of the important tasks in data processing and data mining. To build casebased reasoning（CBR） classifier, the attribute number is reduced firstly with the similar rough set. Then the case base is maintained by deletion operation based on case classification. Hence there is less storage space and higher classification accuracy in the CBR classifier system. Experimental results have shown that the proposed classification approach can reach satisfactory classification accuracy and speed as compared with the traditional CBR classifier and the neural network classification system.

关 键 词：分类 案例推理 属性约简 案例删除 案例库维护 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]