Rough集规则知识获取研究中的不一致性问题

The Inconsistency in Rough Set Based Rule Generation

讨论数据挖掘问题 ,即从原始数据中构造决策规则。重点考虑不一致情况下的规则知识获取问题 ,即从包含不一致信息的数据中获取得到缺省规则 ,并研究在不一致条件下的决策规则选择策略 ,使之能够在不完全、不一致的条件下进行推理。同时将在 Skowron缺省规则获取算法的基础上 ,根据对不一致性的分析 ,提出从包含不一致信息的决策表中获取缺省规则 ,并能够对任意待识样本进行处理的方法。

As the amount of information in the world is steadily increasing, there is a growing demand for tools for analyzing the information. In this paper the authors investigate the problem of data mining,that is, constructing decision rules from a set of primitive input data. The main contention of the present work is that there is a need for generating decision rules and reasoning in inconsistency. Propositional default rules are generated in this paper. Based on the default rule generation method of Skowron and the inconsistency analysis, the authors present a method for default rule generation from a decision table and its reasoning method. A new stratagem for choosing the most suitable rule from a set of conflicting rules is developed. Any unseen sample can be processed with the rules generated with this method.