A Novel Generalized Fuzzy Canonical Correlation Analysis Framework for Feature Fusion and Recognition

作者：Yang, Jing; Sun, Quan-Sen^*

来源：Neural Processing Letters, 2017, 46(2): 521-536.

DOI：10.1007/s11063-017-9600-z

• Canonical correlation analysis
• Generalized canonical correlation analysis
• Fuzzy membership
• Feature fusion
• Dimensionality reduction

In this paper, a novel CCA-based dimensionality reduction method called generalized fuzzy canonical correlation analysis (GFCCA) is proposed. GFCCA combines the generalized canonical correlation analysis and fuzzy set theory. GFCCA redefines the fuzzy between-class and within-class scattermatrices that relate directly to the samples distribution information. For nonlinear separated problems, we extend the kernel extension of GFCCA with positive definite kernels and indefinite kernels. Experiments on real-world data sets are performed to test and evaluate the effectiveness of the proposed algorithms.

• 出版日期2017-10
• 单位南京理工大学