基于深度学习的监督型典型相关分析

doi:10.19678/j.issn.1000-3428.0061291

计算机工程 ›› 2022, Vol. 48 ›› Issue (5): 222-228. doi: 10.19678/j.issn.1000-3428.0061291

基于深度学习的监督型典型相关分析

张恒¹, 陈晓红¹, 蓝宇翔¹, 李舜酩²

1. 南京航空航天大学理学院, 南京 211106;
2. 南京航空航天大学能源与动力学院, 南京 211106

收稿日期:2021-03-26 修回日期:2021-05-19 发布日期:2022-05-10
作者简介:张恒(1998—),男,硕士研究生,主研方向为模式识别、机器学习;陈晓红,副教授、博士;蓝宇翔,硕士研究生;李舜酩,教授、博士。
基金资助:
国家自然科学基金（11971231，12111530）；国家重点研发计划（2018YFB2003300）。

Supervised Canonical Correlation Analysis Based on Deep Learning

ZHANG Heng¹, CHEN Xiaohong¹, LAN Yuxiang¹, LI Shunming²

1. College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China

Received:2021-03-26 Revised:2021-05-19 Published:2022-05-10

摘要/Abstract

摘要： 典型相关分析（CCA）是利用综合变量对之间的相关关系反映两组指标之间整体相关性的多元统计方法。传统的CCA方法无法有效利用样本的标签信息，导致准确率降低。将类信息融入到深度学习与CCA相结合的深度典型相关分析中，提出一种监督型降维方法DL-SCCA，用于处理带标签的非线性可分数据。在2个独立的深度神经网络（DNN）结构上，增加1个公共的输出维数与数据集类别数相同的全连接层，并且以softmax函数作为该层的激活函数，输出带有概率意义的编码向量。在此基础上，利用全连接输出与样本标签信息之间的交叉熵对DNN进行训练，获得分类性能较优的低维特征。实验结果表明，该方法采用最近邻分类器和网络本身结构得到的分类准确率分别为98.00%和97.82%，相比CCA、DisCCA、DCCA等方法，能够有效利用样本的标签信息，并且具有较优的分类性能。

Abstract: Canonical Correlation Analysis (CCA) is a multivariate statistical method, which uses the correlation between comprehensive variable pairs to reflect the overall correlation between two groups of indicators.The traditional CCA method can not effectively use the label information of samples, resulting in low accuracy.The class information is integrated into the Deep Canonical Correlation Analysis (DCCA) combined with deep learning and CCA, and a supervised dimensionality reduction method, DL-SCCA, is proposed to deal with nonlinear separable data with labels.Different Deep Neural Networks (DNN) are established for the samples of two views, and their nonlinear transformation and correlation analysis are carried out.Based on the structure of Deep Neural Networks (DNN), a full connection layer with the same common output dimension and number of categories of the data set is added to the two independent DNN.The softmax function is used as the activation function of this layer, which outputs coding vector with probability significance.On this basis, the DNN is trained using the cross-entropy between the full connection output and the sample label information, and low-dimensional features with better classification performance are obtained.The experimental results show that the classification accuracy of this method is 98.00% and 97.82% by using nearest neighbor classifier and network structure respectively.Compared with CCA, DisCCA, and DCCA, the proposed method can effectively use the label imformation of samples and has better classification performace.

Key words: Canonical Correlation Analysis(CCA), Deep Neural Network(DNN), cross-entropy, data dimension reduction, supervised learning

中图分类号:

TP18

张恒, 陈晓红, 蓝宇翔, 李舜酩. 基于深度学习的监督型典型相关分析[J]. 计算机工程, 2022, 48(5): 222-228.

ZHANG Heng, CHEN Xiaohong, LAN Yuxiang, LI Shunming. Supervised Canonical Correlation Analysis Based on Deep Learning[J]. Computer Engineering, 2022, 48(5): 222-228.

https://www.ecice06.com/CN/Y2022/V48/I5/222

图/表 7

20220805181817

20220805181820

20220805181824

20220805181828

20220805181832

20220805181836

20220805181840

参考文献

[1] HOTELLING H.Relations between two sets of variates[J].Biometrika, 1936, 28(3/4):321-377.
[2] HARDOON D R, SZEDMAK S, SHAWE-TAYLOR J.Canonical correlation analysis:an overview with application to learning methods[J].Neural Computation, 2004, 16(12):2639-2664.
[3] 张恩豪, 陈晓红, 刘鸿, 等.基于典型相关分析的多视图降维算法综述[J].计算机工程, 2020, 46(2):1-10. ZHANG E H, CHEN X H, LIU H, et al.Overview of multi-view dimension reduction algorithm based on canonical correlation analysis[J].Computer Engineering, 2020, 46(2):1-10.(in Chinese)
[4] LUO J, TJAHJADI T.Multi-set canonical correlation analysis for 3D abnormal gait behaviour recognition based on virtual sample generation[J].IEEE Access, 2020, 8:32485-32501.
[5] HE Z C, YANG Y, QIAO L, et al.Canonical correlation analysis and key performance indicator based fault detection scheme with application to marine diesel supercharging systems[C]//Proceeding of Chinese Control Conference.Guangzhou, China:[s.n.], 2019:5156-5160.
[6] 白云歌, 郭炳晖, 米志龙, 等.面向互联网金融平台的违约风险量化模型[J].计算机工程, 2018, 44(12):108-114. BAI Y G, GUO B H, MI Z L, et al.Quantitative model of default risk for internet financial platform[J].Computer Engineering, 2018, 44(12):108-114.(in Chinese)
[7] SUN T K, CHEN S C, YANG J Y, et al.A novel method of combined feature extraction for recognition[C]//Proceedings of the 8th IEEE International Conference on Data Mining.Washington D.C., USA:IEEE Press, 2008:1043-1048.
[8] YANG M, SUN S L.Multi-view uncorrelated linear discriminant analysis with applications to handwritten digit recognition[C]//Proceedings of International Joint Conference on Neural Networks.Washington D.C., USA:IEEE Press, 2014:4175-4181.
[9] SUN S L, XIE X J, YANG M.Multiview uncorrelated discriminant analysis[J].IEEE Transactions on Cybernetics, 2016, 46(12):3272-3284.
[10] SHAWE-TAYLOR J, CRISTIANINI N.Kernel methods for pattern analysis[M].Cambridge, USA:Cambridge University Press, 2005.
[11] GAO J J, LI F Z, WANG B J, et al.Unsupervised nonlinear adaptive manifold learning for global and local information[J].Tsinghua Science and Technology, 2020, 26(2):163-171.
[12] RAMACHANDRAM D, TAYLOR G W.Deep multimodal learning:a survey on recent advances and trends[J].IEEE Signal Processing Magazine, 2017, 34(6):96-108.
[13] MELZER T, REITER M, BISCHOF H.Kernel canonical correlation analysis[J].Journal of Financial Economic Policy, 2001, 6(2):179-196.
[14] LOPEZ-PAZ D, SRA S, SMOLA A, et al.Randomized nonlinear component analysis[C]//Proceedings of the 31st International Conference on Machine Learning.New York, USA:ACM Press, 2014:1359-1367.
[15] SUN T K, CHEN S C.Locality preserving CCA with applications to data visualization and pose estimation[J].Image and Vision Computing, 2007, 25(5):531-543.
[16] ZHANG H J, ZHANG J X, LIU Y W, et al.Multiset canonical correlations analysis with global structure preservation[J].IEEE Access, 2020, 8:53595-53603.
[17] ANDREW G, ARORA R, BILMES J A.Deep canonical correlation analysis[C]//Proceedings of the 30th International Conference on Machine Learning.New York, USA:ACM Press, 2013:1247-1255.
[18] WANG W, ARORA R, LIVESCU K, et al.On deep multi-view representation learning[C]//Proceedings of the 32nd International Conference on Machine Learning.New York, USA:ACM Press, 2015:1083-1092.
[19] LIU Y, LI Y, YUAN Y H, et al.Supervised deep canonical correlation analysis for multiview feature learning[C]//Proceedings of International Conference on Neural Information Processing.Berlin, Germany:Springer, 2017:575-582.
[20] ELMADANY N E D, HE Y F, LING G.Multiview learning via deep discriminative canonical correlation analysis[C]//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing.Washington D.C., USA:IEEE Press, 2016:2409-2413.
[21] YANG Q, GU Y D, WU D S.Survey of incremental learning[C]//Proceedings of the 31st Chinese Control and Decision Conference.Washington D.C., USA:IEEE Press, 2019:399-404.

选择文件类型/文献管理软件名称

选择包含的内容

基于深度学习的监督型典型相关分析

Supervised Canonical Correlation Analysis Based on Deep Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	周炫余, 吴莲华, 郑勤华, 肖天星, 王紫璇, 张思敏. 联合语义提示和记忆增强的弱监督跳绳视频异常检测方法[J]. 计算机工程, 2024, 50(7): 87-95.
[2]	张正康, 杨丹, 聂铁铮, 寇月. 基于图结构聚类的自监督学习疾病诊断方法[J]. 计算机工程, 2024, 50(7): 360-371.
[3]	余长宏, 许孔豪, 张泽, 高明. 基于分割点改进孤立森林的网络入侵检测方法[J]. 计算机工程, 2024, 50(6): 148-156.
[4]	李永飞, 李铭洋, 常鑫, 曹可欣. 基于可解释性深度学习的物联网水质监测数据异常检测[J]. 计算机工程, 2024, 50(6): 179-187.
[5]	顾永跟, 高凌轩, 吴小红, 陶杰. 非独立同分布下联邦半监督学习的数据分享研究[J]. 计算机工程, 2024, 50(6): 188-196.
[6]	张慧妍, 梁勇, 兰景宏, 赵强. 基于记忆模块与过滤式生成对抗网络的入侵检测方法[J]. 计算机工程, 2024, 50(6): 197-207.
[7]	张宝鑫, 杨丹, 聂铁铮, 寇月. 基于自监督的多视角图协同过滤推荐方法[J]. 计算机工程, 2024, 50(5): 100-110.
[8]	李晶, 李健, 陈海丰, 张倩, 王丽燕, 裴二成. 基于关键区域遮挡与重建的人脸表情识别[J]. 计算机工程, 2024, 50(5): 241-249.
[9]	宫阿娟, 潘天荣. 多病种眼底疾病诊断的深度学习策略讨论[J]. 计算机工程, 2024, 50(5): 363-372.
[10]	王琳, 黄浩. 引入预训练表示混合矢量量化和CTC的语音转换[J]. 计算机工程, 2024, 50(4): 313-320.
[11]	刘帅威, 李智, 王国美, 张丽. 基于Transformer和GAN的对抗样本生成算法[J]. 计算机工程, 2024, 50(2): 180-187.
[12]	何银银, 胡静, 陈志泊, 张荣国. 融合门控变换机制和GAN的低光照图像增强方法[J]. 计算机工程, 2024, 50(2): 247-255.
[13]	刘晓黎, 王轶彤. 基于自监督学习的多密度图会话推荐[J]. 计算机工程, 2023, 49(9): 60-68, 78.
[14]	王书朋, 何引弟. 融合特征注意力机制的非均匀光照图像增强算法[J]. 计算机工程, 2023, 49(8): 232-239.
[15]	马娜, 温廷新, 贾旭, 李晓会. 复杂光照条件下自适应的车脸重识别模型[J]. 计算机工程, 2023, 49(8): 275-282, 290.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于深度学习的监督型典型相关分析

Supervised Canonical Correlation Analysis Based on Deep Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献

相关文章 15

编辑推荐

Metrics

本文评价