摘要
提出了利用相似粗糙集进行范例提取的算法,自动从原始数据中提取典型范例并能获得较高的分类精度.该算法能较好的处理噪声的干扰,减少预设参数的数量,并能直接处理连续数值型属性,避免了复杂的属性离散化的计算.实验结果验证了算法的可行性和有效性.
A case selection algorithm selects representative cases from a large data set for future case-based reasoning tasks. This paper proposes the SRS algorithm, based on similarity-based rough set theory, which selects a reasonable number of the representative cases while maintaining satisfactory classification accuracy. It also can handle noise and inconsistent data. Experimental result has confirmed the algorithm feasibility and the validity.
出处
《小型微型计算机系统》
CSCD
北大核心
2007年第6期1072-1075,共4页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(90305005)资助.
关键词
相似粗糙集
相似关系
范例推理
知识表达系统
分类精度
similarity-rough set
similarity relation
case-based reasoning
information systems
classification accuracy