基于粒子群优化的模糊特征自适应选择方法  

Adaptive Fuzzy Feature Selection Based on Particle Swarm Optimization

作　　者：李林宜[1] 李德仁[2] 

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079 [2]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079

出　　处：《测绘科学技术学报》2011年第2期121-124,共4页Journal of Geomatics Science and Technology

基　　金：国家自然科学基金资助项目(41001255);地理空间信息工程国家测绘局重点实验室经费资助项目(201021);中央高校基本科研业务费专项资金资助项目(4082007)

摘　　要：模糊特征的选择影响着模糊分类的结果。从大量模糊特征中选择出有效特征进行分类,存在着一定的难度。粒子群优化算法(PSO)是基于群体智能的新型进化计算技术,具有自适应、自组织等智能特性,具有强大的寻找最优解的能力。将离散二进制PSO用于模糊特征选择,实现了基于PSO的模糊特征自适应选择方法,并通过航空和卫星遥感影像的模糊分类实验,验证了此方法的有效性。Fuzzy feature selection affects fuzzy classification results;however,it is difficult to select effective fuzzy features from large numbers of fuzzy features in fuzzy classification.Particle swarm optimization（PSO） is a new evolutionary computing technique that is based on swarm intelligence.Because of its intelligent properties such as adaptation and self-organizing,PSO has the strong ability to search for the optimal solutions for optimization problems.Discrete binary PSO was used to get the optimal fuzzy feature combination adaptively,and the fuzzy feature selection method based on PSO was applied to aerial and satellite remote sensing image fuzzy classification.The experimental results showed that the proposed method was effective.

关 键 词：粒子群优化算法 模糊特征选择 模糊分类 自适应 遥感 

分 类 号：P237[天文地球—摄影测量与遥感]