[1]许子微,陈秀宏.自步稀疏最优均值主成分分析[J].智能系统学报,2021,16(3):416-424.[doi:10.11992/tis.201911028]
 XU Ziwei,CHEN Xiuhong.Sparse optimal mean principal component analysis based on self-paced learning[J].CAAI Transactions on Intelligent Systems,2021,16(3):416-424.[doi:10.11992/tis.201911028]
点击复制

自步稀疏最优均值主成分分析(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年3期
页码:
416-424
栏目:
学术论文—机器学习
出版日期:
2021-05-05

文章信息/Info

Title:
Sparse optimal mean principal component analysis based on self-paced learning
作者:
许子微 陈秀宏
江南大学 数字媒体学院,江苏 无锡 214122
Author(s):
XU Ziwei CHEN Xiuhong
School of Digital Media, Jiangnan University, Wuxi 214122, China
关键词:
图像处理主成分分析无监督学习数据降维稀疏最优均值自步学习人脸识别
Keywords:
image processingprincipal component analysisunsupervised learningdata dimension deductionsparseoptimal meanself-paced learningface recognition
分类号:
TP391.4
DOI:
10.11992/tis.201911028
摘要:
主成分分析(PCA)是一种无监督降维方法。然而现有的方法没有考虑样本的差异性,且不能联合地提取样本的重要信息,从而影响了方法的性能。针对以上问题,提出自步稀疏最优均值主成分分析方法。模型以 $ {{L}_{{2,1}}}$ 范数定义损失函数,同时用 $ {L_{{\rm{2,1}}}}$ 范数约束投影矩阵作为正则化项,且将均值作为在迭代中优化的变量,这样可一致地选择重要特征,提高方法对异常值的鲁棒性;考虑到训练样本的差异性,利用自步学习机制实现训练样本由“简单”到“复杂”的学习过程,有效地降低异常值的影响。理论分析和实验结果表明,以上方法能更有效地降低异常值对分类精度的影响,提高分类精度。
Abstract:
Principal component analysis (PCA) can be referred to as an unsupervised dimensionality reduction approach. However, the existing methods do not consider the difference of samples and cannot jointly extract important information of samples, thus affecting the performance of some methods. For the above problems, based on self-paced learning, we proposed a sparse optimal mean PCA algorithm. In our model, loss of function is defined by $ {L_{{\rm{2,1}}}}$ norm, the projection matrix is regularized by $ {L_{{\rm{2,1}}}}$ norm, and the mean value is taken as a variable to be optimized in the iteration. In this way, important features can be consistently selected, and the robustness of the method to outliers can be improved. Considering the difference in training samples, we utilized self-paced learning mechanism to complete the learning process of training samples from “simple” to “complex” so as to effectively reduce the influence of outliers. Theoretical analysis and the empirical study revealed that the proposed method could effectively reduce the influence of noise or outliers on the classification progress, thus improving the effect of the classification.

参考文献/References:

[1] OU Weihua, YOU Xinge, TAO Dacheng, et al. Robust face recognition via occlusion dictionary learning[J]. Pattern recognition, 2014, 47(4):1559-1572.
[2] WEI Lai, ZHOU Rigui, YIN Jun, et al. Latent graph-regularized inductive robust principal component analysis[J]. Knowledge-based systems, 2019, 177:68-81.
[3] HE Jinrong, BI Yingzhou, LIU Bin, et al. Graph-dual Laplacian principal component analysis[J]. Journal of ambient intelligence and humanized computing, 2019, 10(8):3249-3262.
[4] ZHAO Haifeng, WANG Zheng, NIE Feiping. A new formulation of linear discriminant analysis for robust dimensionality reduction[J]. IEEE transactions on knowledge and data engineering, 2018, 31(4):629-640.
[5] 朱换荣, 郑智超, 孙怀江. 面向局部线性回归分类器的判别分析方法[J]. 智能系统学报, 2019, 14(5):959-965
ZHU Huanrong, ZHENG Zhichao, SUN Huaijiang. Locality-regularized linear regression classification-based discriminant analysis[J]. CAAI transactions on intelligent systems, 2019, 14(5):959-965
[6] NIE Feiping, HUANG Heng, DING C, et al. Robust principal component analysis with non-greedy l1-norm maximization[C]//Proceedings of the 22nd International Joint Conference on Artificial Intelligence. Barcelona, Catalonia, Spain, 2011:1433-1438.
[7] NIE Feiping, YUAN Jianjun, HUANG Heng. Optimal mean robust principal component analysis[C]//Proceedings of the 31st International Conference on Machine Learning. Beijing, China, 2014:1062-1070.
[8] ZOU Hui, HASTIE T, TIBSHIRANI R. Sparse principal component analysis[J]. Journal of computational and graphical statistics, 2006, 15(2):265-286.
[9] YI Shuangyan, LAI Zhihui, HE Zhenyu, et al. Joint sparse principal component analysis[J]. Pattern recognition, 2017, 61:524-536.
[10] BENGIO Y, LOURADOUR J, COLLOBERT R, et al. Curriculum learning[C]//Proceedings of the 26th Annual International Conference on Machine Learning. Montreal, Quebec, Canada, 2009:41-48.
[11] KUMAR M P, PACKER B, KOLLER D. Self-paced learning for latent variable models[C]//Proceedings of the 23rd International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada, 2010:1189-1197.
[12] JIANG Lu, MENG Deyu, ZHAO Qian, et al. Self-paced curriculum learning[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence. Austin, Texas, USA, 2015:2694-2700.
[13] YU Hao, WEN Guoqiu, GAN Jiangzhang, et al. Self-paced learning for K-means clustering algorithm[J]. Pattern recognition letters, 2020, 132:69-75.
[14] HU Sixiu, PENG Jiangtao, FU Yingxiong, et al. Kernel joint sparse representation based on self-paced learning for hyperspectral image classification[J]. Remote sensing, 2019, 11(9):1114-1132.
[15] HAJINEZHAD D, SHI Qingjiang. Alternating direction method of multipliers for a class of nonconvex bilinear optimization:convergence analysis and applications[J]. Journal of global optimization, 2018, 70(1):261-288.
[16] HOU Chenping, NIE Feiping, YI Dongyun, et al. Feature selection via joint embedding learning and sparse regression[C]//Proceedings of the 22nd International Joint Conference on Artificial Intelligence. Barcelona, Spain, 2011:1324-1329.
[17] LYONS M J, BUDYNEK J, AKAMATSU S. Automatic classification of single facial images[J]. IEEE transactions on pattern analysis and machine intelligence, 1999, 21(12):1357-1362.
[18] WRIGHT J, YANG A Y, GANESH A, et al. Robust face recognition via sparse representation.[J]. IEEE transactions on pattern analysis and machine intelligence, 2009, 31(2):210-227.
[19] JESORSKY O, KIRCHBERG K J, FRISCHHOLZ R W. Robust face detection using the hausdorff distance[C]//Proceedings of the 3rd International Conference on Audio- and Video-Based Biometric Person Authentication. Halmstad, Sweden, 2001:90-95.
[20] ZHENG Miao, BU Jiajun, CHEN C, et al. Graph regularized sparse coding for image representation[J]. IEEE transactions on image processing, 2011, 20(5):1327-1336.
[21] KUSSUL E, BAIDYK T. Improved method of handwritten digit recognition tested on MNIST database[J]. Image and vision computing, 2004, 22(12):971-981.

相似文献/References:

[1]朱帮助,林 健.基于支持向量数据描述的无标签数据多类分类[J].智能系统学报,2009,4(02):131.
 ZHU Bang-zhu,LIN Jian.Multiclass classification algorithm for unlabeled data using SVDD[J].CAAI Transactions on Intelligent Systems,2009,4(3):131.
[2]李庆武,蔡艳梅,徐立中.基于分块分类的智能视频监控背景更新算法[J].智能系统学报,2010,5(03):272.
 LI Qing-wu,CAI Yan-mei,XU Li-zhong.Background update algorithm based on blocks classification forintelligent video surveillance[J].CAAI Transactions on Intelligent Systems,2010,5(3):272.
[3]杨向林,严 洪,任兆瑞,等.基于PCA特征和融合特征的ECG身份识别方法[J].智能系统学报,2010,5(05):458.[doi:10.3969/j.issn.1673-4785.2010.05.014]
 YANG Xiang-lin,YAN Hong,REN Zhao-rui,et al.A method based on the PCA feature and fusion feature for ECG human identification[J].CAAI Transactions on Intelligent Systems,2010,5(3):458.[doi:10.3969/j.issn.1673-4785.2010.05.014]
[4]邵真天,袁杰.一种基于曲波变换的图像去块算法[J].智能系统学报,2012,7(02):102.
 SHAO Zhentian,YUAN Jie.An image deblocking algorithm based on curvelet transformation[J].CAAI Transactions on Intelligent Systems,2012,7(3):102.
[5]王锦榕,袁学海,刘增良.基于图像处理技术的瞳孔和角膜反射中心提取算法[J].智能系统学报,2012,7(05):423.
 WANG Jinrong,YUAN Xuehai,LIU Zengliang.An extraction method of pupil and corneal reflection centers based on image processing technology[J].CAAI Transactions on Intelligent Systems,2012,7(3):423.
[6]李海林,郭韧,万校基.基于特征矩阵的多元时间序列最小距离度量方法[J].智能系统学报,2015,10(03):442.[doi:10.3969/j.issn.1673-4785.201405047]
 LI Hailin,GUO Ren,WAN Xiaoji.A minimum distance measurement method for amultivariate time series based on the feature matrix[J].CAAI Transactions on Intelligent Systems,2015,10(3):442.[doi:10.3969/j.issn.1673-4785.201405047]
[7]傅博,姜勇,王洪光,等.输电线路巡检图像智能诊断系统[J].智能系统学报,2016,11(1):70.[doi:10.11992/tis.201503043]
 FU Bo,JIANG Yong,WANG Hongguang,et al.Intelligent diagnosis system for patrol check images of power transmission lines[J].CAAI Transactions on Intelligent Systems,2016,11(3):70.[doi:10.11992/tis.201503043]
[8]任晓霞,孙秀明,耿鹏,等.多小波和NSDFB组合域递归滤波多聚焦图像融合[J].智能系统学报,2016,11(2):241.[doi:10.11992/tis.201509017]
 REN Xiaoxia,SUN Xiuming,GENG Peng,et al.Multifocus image fusion using a recursive filter in the combined domain of multiwavelets and NSDFB[J].CAAI Transactions on Intelligent Systems,2016,11(3):241.[doi:10.11992/tis.201509017]
[9]梁义辉,战强.一种面向无线图像传输的视觉平台[J].智能系统学报,2016,11(5):608.[doi:10.11992/tis.201512014]
 LIANG Yihui,ZHAN Qiang.A visual platform for wireless image transmission[J].CAAI Transactions on Intelligent Systems,2016,11(3):608.[doi:10.11992/tis.201512014]
[10]刘欢,王骏,邓赵红,等.堆叠隐空间模糊C回归算法及其在发酵数据多模型建模中的应用[J].智能系统学报,2016,11(5):670.[doi:10.11992/tis.201508015]
 LIU Huan,WANG Jun,DENG Zhaohong,et al.A cascaded hidden space fuzzy C-regression algorithmand its application in multi-model modeling for thefermentation process[J].CAAI Transactions on Intelligent Systems,2016,11(3):670.[doi:10.11992/tis.201508015]

备注/Memo

备注/Memo:
收稿日期:2019-11-19。
基金项目:江苏省研究生科研与实践创新计划项目(JNKY19_074)
作者简介:许子微,硕士研究生,主要研究方向为模式识别、图像处理;陈秀宏,教授,主要研究方向为数字图像处理和模式识别、目标检测与跟踪、优化理论与方法。参与国家自然基金项目2项,主持省部级研究项目3项,省博士后基金1项。获得省部级奖1项、校级教学成果奖1项、市厅级奖6项。发表学术论文120余篇
通讯作者:许子微.E-mail:18256515269@163.com
更新日期/Last Update: 2021-06-25