基于改进粒子群优化的移动界面模式聚类算法  

Mobile Interface Pattern Clustering Algorithm Based on Improved Particle Swarm Optimization

作　　者：贾伟[1,2] 华庆一[1] 张敏军[1] 陈锐[1] 姬翔[1] 王博[1,3] JIA Wei;HUA Qing-yi;ZHANG Min-jun;CHEN Rui;JI Xiang;WANG Bo(School of Information Science and Technology,Northwest University,Xi’an 710127,China;Xinhua College,Ningxia University,Yinchuan 750021,China;School of Computer Science and Technology,Xi’an University of Posts and Telecommunications,Xi’an 710121,China)

机构地区：[1]西北大学信息科学与技术学院,西安710127 [2]宁夏大学新华学院,银川750021 [3]西安邮电大学计算机学院,西安710121

出　　处：《计算机科学》2018年第4期220-226,共7页Computer Science

基　　金：国家自然科学基金资助项目(61272286);高等学校博士学科点专项科研基金资助项目(20126101110006);陕西省工业科技攻关项目(2016GY-123);西北大学科学研究基金资助项目(15NW31)资助

摘　　要：聚类是一种非常有效的信息分析方法。针对现有基于粒子群优化的模糊C均值(Fuzzy C-means,FCM)聚类算法的聚类效果不佳的问题,提出一种基于改进粒子群优化的模糊C均值聚类算法,并将该聚类算法应用到移动界面模式的聚类中。首先,利用直觉模糊熵的几何解释和约束构造合理的直觉模糊熵;然后,在粒子群优化中使用直觉模糊熵判断种群的多样性程度,并引入混沌反向学习策略来提高全局搜索能力;最后,为了增强聚类算法的非线性处理能力,在聚类算法中加入高斯核函数,并将该聚类算法应用到移动界面模式的聚类中。移动界面模式聚类的实验表明,与现有聚类算法相比,文中所提聚类算法具有更好的聚类效果。Clustering is a very efficient method for analyzing information.Focusing on the issue that clustering results of the existing fuzzy C-means clustering algorithms based on particle swarm optimization are not good,a fuzzy C-means clustering algorithm based on improved particle swarm optimization was proposed and applied in mobile interface pattern clustering.Firstly,reasonable intuitionistic fuzzy entropy is constructed by using the geometric interpretation and the constraints of intuitionistic fuzzy entropy.Secondly,in the improved particle swarm optimization,the intuitionistic fuzzy entropy is used to measure the state of particle swarm,and chaotic opposition-based learning is used to improve the global search ability.Finally,the proposed algorithm employs the Gauss kernel function for enhancing nonlinear processing capability,and then it is applied in mobile interface pattern clustering.Experimental results show that the proposed clustering algorithm has better performance in mobile interface pattern clustering than the exis-ting clustering algorithms.

关 键 词：粒子群优化 移动界面模式 聚类 直觉模糊熵 混沌反向学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]