Matrix exponential based discriminant locality preserving projections for feature extraction. (January 2018)

• Record Type: Journal Article
• Authors: Lu, Gui-Fu; Wang, Yong; Zou, Jian; Wang, Zhongqun
• Is Part Of: Neural networks. Volume 97(2018)
• Page Start: 127
• Page End: 136
• Publication Date: 2018-01
• Subjects: Dimensionality reduction -- Discriminant locality preserving projections -- Matrix exponential -- Linear discriminant analysis; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2017.09.014
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Discriminant locality preserving projections (DLPP), which has shown good performances in pattern recognition, is a feature extraction algorithm based on manifold learning. However, DLPP suffers from the well-known small sample size (SSS) problem, where the number of samples is less than the dimension of samples. In this paper, we propose a novel matrix exponential based discriminant locality preserving projections (MEDLPP). The proposed MEDLPP method can address the SSS problem elegantly since the matrix exponential of a symmetric matrix is always positive definite. Nevertheless, the computational complexity of MEDLPP is high since it needs to solve a large matrix exponential eigenproblem. Then, in this paper, we also present an efficient algorithm for solving MEDLPP. Besides, the main idea for solving MEDLPP efficiently is also generalized to other matrix exponential based methods. The experimental results on some data sets demonstrate the proposed algorithm outperforms many state-of-the-art discriminant analysis methods.