Linear discriminant analysis for the small sample size problem: an overview

By Alok Sharma, Kuldip K. Paliwal. 2014

259 citations recorded by the source corpus.

Dimensionality reduction is an important aspect in the pattern classification literature, and linear discriminant analysis (LDA) is one of the most widely studied dimensionality reduction technique. The application of variants of LDA technique for solving small sample size (SSS) problem can be found in many research areas e.g. face recognition, bioinformatics, text recognition, etc. The improvement of the performance of variants of LDA technique has great potential in various fields of research. In this paper, we present an overview of these methods. We covered the type, characteristics and taxonomy of these methods which can overcome SSS problem. We have also highlighted some important datasets and software/packages.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

Relational autoencoder for feature extraction (2017, methodology): “The most famous projection methods are Principal Component Analysis (PCA) [10] and Linear Discriminant Analysis (LDA) [11].”
Linear discriminant analysis: A detailed tutorial (2017, unknown): “The third approach, a well-known solution, is to use the regularization method to solve a singular linear systems [38,57].”
Linear vs. quadratic discriminant analysis classifier: a tutorial (2016, methodology): “Another problem of this method is that the parameter η is just added to perform the inverse of Σ and has no clear mathematical interpretation (Lu et al., 2005; Sharma and Paliwal, 2014).”
Techniques for Automated Machine Learning (2019, methodology): “Feature selection will reduce feature dimensions by principal component analysis (PCA) [19] and linear discriminant analysis (LDA) [77], or filter overlapping features by information gain [75].”