【作者】 张永； 吴晓蓓； 向峥嵘； 胡维礼；

【Author】 Zhang Yong Wu Xiaobei Xiang Zhengrong Hu Weili (School of Automation, Nanjing University of Science and Technology, Nanjing 210094,China)

【机构】 南京理工大学自动化学院；

【摘要】 提出一种基于决策树初始化和遗传算法优化的模糊分类系统的设计方法．该方法首先采用分类和递归树(CART)算法进行决策树的生长,树的修剪过程简化了初始决策树;然后,把修剪后的决策树转化为模糊模型,利用匹茨堡型实数编码的遗传算法优化该模糊模型．为了提高模型的解释性,在遗传算法中利用基于相似性的模型简化方法对模型进行约简．最后利用该方法对Iris问题进行研究,仿真结果验证了该方法的有效性．更多还原

【Abstract】 An approach to construct the fuzzy classification system based on the decision-tree and the genetic algorithm is proposed. First, the initial decision-tree is constructed using the classification and regression tree (CART) algorithm; tree pruning process reduces the initial decision-tree. Secondly, the pruned decision-tree is transformed into a fuzzy system, and the parameters of the fuzzy system are optimized by the Pittsburgh-style real-coded genetic algorithm. In order to improve the interpretability of the fuzzy system, the similarity-driven rule based simplification technique is used to reduce the fuzzy system. The proposed approach is applied to the Iris benchmark classification problem, and the results verify its validity.更多还原