Approximate LDA Technique for Dimensionality Reduction in the Small Sample Size Case

被引：11

作者：

Paliwal, Kuldip K. ^{[1
]}

Sharma, Alok ^{[2
,3
,4
]}

机构：

[1] Griffith Univ, Sch Engn, Brisbane, Qld, Australia

[2] Univ Tokyo, Tokyo, Japan

[3] Griffith Univ, Signal Proc Lab, Brisbane, Qld, Australia

[4] Univ South Pacific, Suva, Fiji

来源：

JOURNAL OF PATTERN RECOGNITION RESEARCH | 2011年 / 6卷 / 02期

关键词：

Approximate linear discriminant analysis (ALDA); dimensionality reduction; small sample size problem; classification accuracy; regularized LDA;

D O I：

10.13176/11.370

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

The regularized linear discriminant analysis (LDA) technique overcomes the small sample size (SSS) problem by adding a regularization parameter to the eigenvalues of within-class scatter matrix. However, it has some drawbacks. In this paper we address its drawbacks and propose an improvement. The proposed technique is experimented on several datasets and promising results have been obtained.

引用

页码：298 / 306

页数：9

共 50 条

[1] Solving the small sample size problem of LDA
Huang, R
Liu, QS
Lu, HQ
Ma, SD
16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS, 2002, : 29 - 32
[2] Dimensionality reduction based on SVM and LDA, and its application to classification technique
Yang, Bo
Transactions of Nanjing University of Aeronautics and Astronautics, 2009, 26 (04) : 306 - 312
[3] Theoretical analysis of direct LDA in small sample size problem
Zhao, Wu-Feng
Shen, Hai-Bin
Yan, Xiao-Lang
Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2009, 31 (11): : 2632 - 2636
[4] An efficient algorithm to solve the small sample size problem for LDA
Zheng, WM
Zhao, L
Zou, CR
PATTERN RECOGNITION, 2004, 37 (05) : 1077 - 1079
[5] An Efficient Dimensionality Reduction Approach for Small-sample Size and High-dimensional Data Modeling
Qiu, Xintao
Fu, Dongmei
Fu, Zhenduo
JOURNAL OF COMPUTERS, 2014, 9 (03) : 576 - 580
[6] A Revised Formation of Trace Ratio LDA for Small Sample Size Problem
Li, Zhengxin
Nie, Feiping
Wang, Rong
Li, Xuelong
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, : 1 - 7
[7] Linear dimensionality reduction using relevance weighted LDA
Tang, EK
Suganthan, PN
Yao, X
Qin, AK
PATTERN RECOGNITION, 2005, 38 (04) : 485 - 493
[8] Representative null space LDA for discriminative dimensionality reduction
He, Zaixing
Wu, Mengtian
Zhao, Xinyue
Zhang, Shuyou
Tan, Jianrong
PATTERN RECOGNITION, 2021, 111
[9] Weighted piecewise LDA for solving the small sample size problem in face verification
Kyperountas, Marios
Tefas, Anastasios
Pitas, Ioannis
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (02): : 506 - 519
[10] Comparing LDA with pLSI as a dimensionality reduction method in document clustering
Masada, Tomonari
Kiyasu, Senya
Miyahara, Sueharu
LARGE-SCALE KNOWLEDGE RESOURCES: CONSTRUCTION AND APPLICATION, 2008, 4938 : 13 - 26

← 1 2 3 4 5 →