Pawlak Rough Set Model, Medical Reasoning and Rule Mining
Pawlak Rough Set Model, Medical Reasoning and Rule Mining
复制标题
Pawlak 粗糙集模型、医学推理和规则挖掘
DOI：
10.1007/11908029_7
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
S. Tsumoto
中科院分区：
文献类型：
--
作者：
S. Tsumoto
本文综述了Pawlak的粗糙集模型与医学推理之间的对应关系的两个重要问题。粗糙集的第一个主要思想是，一个给定的概念可以被基于划分的知识近似为上、下近似。有趣的是，这些近似对应于区别医学诊断的聚焦机制；上近似作为候选的选择，而下近似作为最终诊断的结论。粗糙集的第二个思想是，一个概念，即观测，可以表示为给定数据集中的划分，其中粗糙集提供了从给定数据中归纳规则的方法。因此，该模型可用于从医学数据库中提取基于规则的知识。特别是，基于聚焦机制的规则归纳是以自然的方式获得的。
This paper overviews the following two important issues on the correspondence between Pawlak’s rough set model and medical reasoning. The first main idea of rough sets is that a given concept can be approximated by partition-based knowledge as upper and lower approximation. Interestingly, thes approximations correspond to the focusing mechanism of differential medical diagnosis; upper approximation as selection of candidates and lower approximation as concluding a final diagnosis. The second idea of rough sets is that a concept, observations can be represented as partitions in a given data set, where rough sets provides a rule induction method from a given data. Thus, this model can be used to extract rule-based knowledge from medical databases. Especially, rule induction based on the focusing mechanism is obtained in a natural way.