Another variant of robust fuzzy PCA with initial membership estimation

Authors:
Gyeongyong Heo;Seong Hoon Kim;Young Woon Woo;Imgeun Lee
Affiliations:
Visual Media Center, Dong-Eui University, Korea;Dept. of Software Engineering, Kyungpook National University, Korea;Dept. of Multimedia Engineering, Dong-Eui University, Korea;Dept. of Visual Information Engineering, Dong-Eui University, Korea
Venue:
ACIIDS'11 Proceedings of the Third international conference on Intelligent information and database systems - Volume Part II
Year:
2011

Citing 4
Cited 0

A Survey of Outlier Detection Methodologies

Artificial Intelligence Review
2009 Special Issue: RKF-PCA: Robust kernel fuzzy PCA

Neural Networks
An improved algorithm finding nearest neighbor using Kd-trees

LATIN'08 Proceedings of the 8th Latin American conference on Theoretical informatics
Fuzzy auto-associative neural networks for principal component extraction of noisy data

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Principal component analysis (PCA) is a well-known method for dimensionality reduction and feature extraction. PCA has been applied in many areas successfully, however, one of its problems is noise sensitivity due to the use of sum-square-error. Several variants of PCA have been proposed to resolve the problem and, among the variants, improved robust fuzzy PCA (RF-PCA2) demonstrated promising results. RF-PCA2, however, still can be affected by noise due to equal initial membership values for all data points. The fact that RF-PCA2 is still based on sum-square-error is another reason for noise sensitivity. In this paper, a variant of RF-PCA2 called RF-PCA3 is proposed. The proposed algorithm modifies the objective function of RF-PCA2 to allow some increase of sum-square-error and calculates initial membership values using data distribution. RF-PCA3 outperforms RF-PCA2, which is supported by experimental results.