Ordinal discriminative canonical correlation analysis

被引：0

作者：

Zhou, Hang-Xing ^{[1
]}

Chen, Song-Can ^{[1
]}

机构：

[1] College of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing

来源：

Ruan Jian Xue Bao/Journal of Software | 2014年 / 25卷 / 09期

关键词：

Canonical correlation analysis; Classification; Discrimination analysis; Information fusion; Ordinal regression;

D O I：

10.13328/j.cnki.jos.004649

中图分类号：

学科分类号：

摘要：

Multi-View learning is a method to improve the robustness and learning performance of single-view learning by fusing the complementary information. Canonical correlation analysis (CCA) which is used to analyze correlation between two datasets of the same objects is an important method for multi-view feature fusion. CCA aims to seek a pair of projections associated with the two sets of data such that they are maximally correlated. However, CCA results in constraint of the classification performance due to not utilizing the class information or ordinal information of different classes for some applications in which the data labels are ordinal. In order to compensate such a shortcoming, ordinal discriminative canonical correlation analysis (OR-DisCCA) is proposed in this paper by incorporating the class information and ordinal information for extending the traditional CCA. The experimental results show that OR-DisCCA outperforms existing related methods. © Copyright 2014, Institute of Software, the Chinese Academy of Science. All Rights Reserved.

引用

页码：2018 / 2025

页数：7

共 25 条

[1]

Hotelling H., Relations between two sets of variates, Biometrika, 28, 3-4, pp. 321-377, (1936)

[2]

Hardoon D.R., Szedmak S., Shawe T.J., Canonical correlation analysis: An overview with application to learning methods, Neural Computation, 16, 12, pp. 2639-2664, (2004)

[3]

Yan Y., Xiu P., Zhi X., A new fuzzy approach for handling class labels in canonical correlation analysis, Neurocomputing, 71, 7-9, pp. 1735-1740, (2008)

[4]

Feng W.W., Kim B.U., Yu Y.Z., Real-Time data driven deformation using kernel canonical correlation analysis, ACM Trans. on Graphics, 27, 3, (2008)

[5]

Li Y.O., Adali T., Wang W., Calhoun V.D., Joint blind source separation by multiset canonical correlation analysis, IEEE Trans. on Signal Processing, 57, 10, pp. 3918-3929, (2009)

[6]

Sun Q.S., Zeng S.G., Liu Y., Heng P.A., Xia D.S., A new method of feature fusion and its application in image recognition, Pattern Recognition, 38, 12, pp. 2437-2448, (2005)

[7]

Peng Y., Zhang D.Q., Zhang J.C., A new canonical correlation analysis algorithm with local discrimination, Neural Processing Letters, 31, 1, pp. 1-15, (2010)

[8]

Arandjelovic Q., Discriminative extended canonical correlation analysis for pattern set matching, Machine Learning, 94, 3, pp. 353-370, (2014)

[9]

Ji Z., Jing P., Su Y., Pang Y., Rank canonical correlation analysis and its application in visual search reranking, Signal Processing, 93, 8, pp. 2352-2360, (2013)

[10]

Sun T.K., Chen S.C., Yang J.Y., Shi P.F., A novel method of combined feature extraction for recognition, Proc. of the 8th IEEE Int'l Conf. on Data Mining, pp. 1043-1048, (2008)

← 1 2 3 →