基于视图相关因子的多视图数据竞争聚类算法  

View correlation factor based multi-view data competition clustering algorithm

作　　者：苏辉[1] 葛洪伟[1,2] 张涛[1] 杨金龙[1] SU Hui;GE Hongwei;ZHANG Tao;YANG Jinlong(School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China;Ministry of Education Key Laboratory of Advanced Process Control for Light Industry(Jiangnan University), Wuxi,Jiangsu 214122, China)

机构地区：[1]江南大学物联网工程学院,江苏无锡214122 [2]轻工过程先进控制教育部重点实验室(江南大学),江苏无锡214122

出　　处：《计算机工程与应用》2017年第3期100-105,159,共7页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61402203);江苏省普通高校研究生科研创新计划项目(No.KYLX_1122);江苏省高校优势学科建设工程资助项目

摘　　要：针对现有的单视图数据竞争聚类算法无法高效处理多视图数据的问题,提出了基于视图相关因子的多视图数据竞争聚类算法。首先,为了描述不同视图之间的相关性定义了一种视图相关性因子;然后,将视图相关因子与谱方法关于拉普拉斯矩阵的目标函数最大化问题结合,建立一个联合目标函数,使得不同视图之间的信息相互影响,以充分利用多视图的信息。通过解决联合目标函数的优化问题,得到每个视图的优化嵌入矩阵;最后,将得到的优化嵌入矩阵用于数据竞争聚类算法中。在人工和真实数据集上的仿真实验结果表明,新算法比现有的数据竞争聚类算法具有更高的聚类性能。Since the existing single view data competition clustering algorithm has poor performance on multiple viewsdata,a view correlation factor based multi-view data competition clustering algorithm is proposed.Firstly,a view correlationfactor is defined as the correlation between different views.Next,the view correlation factors are combined with spectralobjective function maximum problem,and a joint objective function which can make full use of information from differentviews is built to make the information interaction between different views.By solving the joint objective functionoptimization problem,the optimized embedding matrices of each view are obtained.Then,the optimized embedding matricesare used in data competition clustering algorithm.The simulation results on synthetic and real life datasets show thatthe proposed algorithm can obtain better performance than existing data competition clustering algorithm.

关 键 词：聚类 数据竞争 聚合场 多视图 视图相关因子 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]