基于决策粗糙集的模糊分类模型

Fuzzy Classification Model Based on Decision-theoretic Rough Set

提出一种新的模糊分类模型,该模型利用决策粗糙集指导模糊分类模型结构的设计.首先采用模糊C均值聚类算法对连续属性离散化同时对输入空间进行模糊划分;然后利用两步搜索策略计算离散化决策表的约简,删除冗余的条件属性;从约简后的决策表中提取决策规则,再将决策规则转换成模糊分类规则,从而建立了模糊分类模型.模糊分类模型的规则物理含义明确、形式简化,并且不需要再采用学习算法调整模型的参数.最后利用UCI(university of California irvine)标准数据集与现有的一些分类算法进行了比较,仿真实验结果证明了本文提出的模型是有效的.

A new fuzzy classification model is proposed. The proposed model uses a decision-theoretic rough set to design the structure of a fuzzy classification model. The fuzzy C-means clustering algorithm is used to trans- form the continuous attributes into diseretized ones and to partition the fuzzy input space. A heuristic attribute reduction algorithm based on a two-step search strategy＋ deals with the discretized decision table to remove re- dundant-condition attributes. Then, concise decision rules are extracted. The rules of the fuzzy classification model are obtained according to the extracted decision rules. The fuzzy classification rules of the proposed model have clear physical meaning and a simplified structure. Moreover, a Learning algorithm is no longer needed to optimize the parameters of the fuzzy model. Finally, the proposed model is compared ,with some ex- isting classification algorithms by experiments using some UCI data sets. The experiment results show that the proposed model is effective,