首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种新的广义鲁棒主成分分析(GRPCA)算法研究及应用
引用本文:侯旭珂,杨宏伟,马方,赵丽娜.一种新的广义鲁棒主成分分析(GRPCA)算法研究及应用[J].北京化工大学学报(自然科学版),2018,45(4):82-85.
作者姓名:侯旭珂  杨宏伟  马方  赵丽娜
作者单位:北京化工大学理学院,北京,100029;北京化工大学信息中心,北京,100029
基金项目:国家自然科学基金(11301021/11571031)
摘    要:为恢复被混合噪声污染的低秩矩阵,提出了一种新的广义鲁棒主成分分析(GRPCA)算法。它通过最小化核范数、1范数和2,1范数的组合问题,从观测矩阵中分离出低秩部分和混合噪声部分,并用随机排序的交替方向乘子法求解。利用本文方法进行垃圾邮件分类的实验结果表明,与经典的主成分分析(PCA)和鲁棒主成分分析(RPCA)算法相比,本文方法可以有效提高垃圾邮件分类的精确度和稳定性。

关 键 词:广义鲁棒主成分分析(GRPCA)  降维  k近邻(kNN)  支持向量机(SVM)
收稿时间:2017-09-06

A new generalized robust principal component analysis (GRPCA) algorithm
HOU XuKe,YANG HongWei,MA Fang,ZHAO LiNa.A new generalized robust principal component analysis (GRPCA) algorithm[J].Journal of Beijing University of Chemical Technology,2018,45(4):82-85.
Authors:HOU XuKe  YANG HongWei  MA Fang  ZHAO LiNa
Institution:1. Faculty of Science, Beijing University of Chemical Technology, Beijing 100029, China;2. Center for Information Technology, Beijing University of Chemical Technology, Beijing 100029, China
Abstract:A new generalized robust principal component analysis (GRPCA) algorithm is proposed in order to recover the low-rank matrix with mixed noise pollution. It separates the low-rank part and the mixed noise part from the observation matrix by minimizing the combination of the kernel norm, the 1 norm, and the 2,1 norm, and then solving by a randomly permuted alternating direction multiplier method. Using spam classification as an example and a comparison with the classic methods PCA and RPCA shows that this method can effectively improve the accuracy and robustness of spam classification.
Keywords:generalized robust principal component analysis(GRPCA)                                                                                                                        dimensionality reduction                                                                                                                        k-nearest neighber (kNN)" target="_blank">k-nearest neighber (kNN)')">k-nearest neighber (kNN)                                                                                                                        support vector machines(SVM)
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《北京化工大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《北京化工大学学报(自然科学版)》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号