一种基于多神经树集成的分类模型  

Classification model based on neural tree ensemble

作　　者：齐峰[1] 刘希玉[1] 

机构地区：[1]山东师范大学管理与经济学院,济南250014

出　　处：《控制与决策》2010年第11期1684-1688,共5页Control and Decision

基　　金：国家自然科学基金项目(60873058;60743010);山东省"泰山学者"建设工程专项项目

摘　　要：针对数据挖掘领域分类问题的特点,提出了基于多神经树集成的分类模型(CMBNTE).该模型利用改进遗传规划算法和粒子群算法,实现单个神经树模型的优化;借鉴集成学习思想,将多个神经树模型组合成最终的分类模型.在6个UCI数据集上的实验结果表明,该模型能较好地解决分类问题,尤其适用于多分类属性的复杂分类问题.A classification model based on neural tree ensemble is presented for the characteristics of classification in data mining,which establishes a single neural tree model by using modified genetic programming and particle swarm optimization for its optimization.Then more neural tree models are combined to form the final classification model by the idea of ensemble learning.Experimental results show that this model is effective for the classification,and especially for the complex classification with multi-class attributes.

关 键 词：神经树模型 遗传规划 粒子群算法 集成学习 分类 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]