[1]郝敬琪,胡立华,张素兰,等.基于非负矩阵分解的均方残差多视图聚类算法[J].计算机技术与发展,2023,33(12):65-71.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 009]
　HAO Jing-qi,HU Li-hua,ZHANG Su-lan,et al.Mean Square Residual Multi-view Clustering Algorithm Based on Non-negative Matrix Factorization[J].,2023,33(12):65-71.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 009]
点击复制

基于非负矩阵分解的均方残差多视图聚类算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年12期
页码:
65-71
栏目:
媒体计算
出版日期:
2023-12-10

文章信息/Info

Title:
Mean Square Residual Multi-view Clustering Algorithm Based on Non-negative Matrix Factorization
文章编号:
1673-629X(2023)12-0065-07
作者:
郝敬琪; 胡立华; 张素兰; 张继福
太原科技大学 计算机科学与技术学院,山西 太原 030024
Author(s):
HAO Jing-qi; HU Li-hua; ZHANG Su-lan; ZHANG Ji-fu
School of Computer Science and Technology,Taiyuan University of Science and Technology,Taiyuan 030024,China
关键词:
均方残差; 非负矩阵分解; 流行正则化; 希尔伯特-施密特独立性准则; 谱聚类
Keywords:
mean squared residue; non -negative matrix factorization; manifold regularization; Hilbert - Schmidt independence criterion; spectral clustering
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 12. 009
摘要:
针对高维海量数据,现有的多视图聚类方法存在无法发现高维视图隐藏信息、聚类效果差等问题。 结合均方残差( Mean Squared Residue,MSR) 思想,提出了一种基于非负矩阵分解的均方
残差多视图聚类方法(Mean Squared Residue Non-negative Matrix Factorization,MSRNMF)。 首先,采用改进的非负矩阵分解方法结合流形学习、希尔伯特-施密特独立性准则计算各单视
图的系数矩阵,不仅降低了多视图中各个视图的维度,而且有效地提取了高维数据中的隐藏信息;其次,采用谱聚类算法对各单视图的系数矩阵进行聚类,获得单视图聚类簇;接着,利用均方残差
思想,针对各单视图聚类结果进行融合,得到最终多视图聚类结果;最后,以标准数据集和古建数据集为对象进行验证,实验结果表明该算法在精度上优于 MVCF,GPSNMF,GPMVNMF,DMF 和 MCLES, 在古建筑集上效果明显,进而验证了算法的有效性。
Abstract:
For high-dimensional massive data,the existing multi-view clustering methods have some problems,such as failing to discoverthe hidden information of high-dimensional view and poor clustering effect. With the idea of mean square residuals ( MSR) ,a method ofclustering with mean squared residue based on non-negative matrix factorization ( MSRNMF) is proposed. Firstly,the improved non-negative matrix factorization method combined with manifold learning and Hilbert-Schmidt independence criterion is used to calculate thecoefficient matrix of each single view,which not only reduces the dimensions of each view in the multi-view,but also effectively extractsthe hidden information in the high-dimensional data. Secondly,spectral clustering algorithm is used to cluster the coefficient matrix ofeach single view,and the single view cluster is obtained. Then using the idea of mean square residual,the clustering results of each singleview are fused to obtain the final multi-view clustering results. Finally,standard data sets and ancient construction data sets are used forverification. The experimental results show that the accuracy of the proposed algorithm is better than that of MVCF, GPSNMF,GPMVNMF,DMF and MCLES,and the effectiveness of it is verified.

相似文献/References:

[1]高宏娟 潘晨.基于非负矩阵分解的人脸识别算法的改进[J].计算机技术与发展,2007,(11):63.
　GAO Hong-juan,PAN Chen.Improved Face Recognition Algorithm Based on Non- Negative Matrix Factorization[J].,2007,(12):63.
[2]李振博,徐桂琼,査九. 基于用户谱聚类的协同过滤推荐算法[J].计算机技术与发展,2014,24(09):59.
　LI Zhen-bo,XU Gui-qiong,ZHA Jiu. A Collaborative Filtering Recommendation Algorithm Based on User Spectral Clustering[J].,2014,24(12):59.
[3]祝加祥[],胡鹏程[],何璇[],等. 基于滑动窗非负矩阵分解的运动目标检测方法[J].计算机技术与发展,2017,27(01):20.
　ZHU Jia-xiang[],HU Peng-cheng[],HE Xuan[],et al. Moving Target Detection Method Based on Non-negative Matrix Factorization of Sliding Window[J].,2017,27(12):20.

更新日期/Last Update: 2023-12-10