Linear discriminant analysis for two classes via removal of classification structure

Mayer Aladjem

doi:10.1109/34.574805

Linear discriminant analysis for two classes via removal of classification structure

Mayer Aladjem

Department of Electrical & Computer Engineering

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

Abstract

A new method for two-class linear discriminant analysis, called "removal of classification structure," is proposed. Its novelty lies in the transformation of the data along an identified discriminant direction into data without discriminant information and iteration to obtain the next discriminant direction. It is free to search for discriminant directions oblique to each other and ensures that the informative directions already found will not be chosen again at a later stage. The efficacy of the method is examined for two discriminant criteria. Studies with a wide spectrum of synthetic data sets and a real data set indicate that the discrimination quality of these criteria can be improved by the proposed method.

Original language	English
Pages (from-to)	187-192
Number of pages	6
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	19
Issue number	2
DOIs	https://doi.org/10.1109/34.574805
State	Published - 1 Dec 1997

Keywords

Dimension reduction
Discriminant plots
Exploratory data analysis
Linear discriminant analysis
Structure removal

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

10.1109/34.574805

Cite this

@article{c3e3d7ae35074c08b6d7060e585dceee,

title = "Linear discriminant analysis for two classes via removal of classification structure",

abstract = "A new method for two-class linear discriminant analysis, called {"}removal of classification structure,{"} is proposed. Its novelty lies in the transformation of the data along an identified discriminant direction into data without discriminant information and iteration to obtain the next discriminant direction. It is free to search for discriminant directions oblique to each other and ensures that the informative directions already found will not be chosen again at a later stage. The efficacy of the method is examined for two discriminant criteria. Studies with a wide spectrum of synthetic data sets and a real data set indicate that the discrimination quality of these criteria can be improved by the proposed method.",

keywords = "Dimension reduction, Discriminant plots, Exploratory data analysis, Linear discriminant analysis, Structure removal",

author = "Mayer Aladjem",

note = "Funding Information: The author wishes to thank associate editor Prof. D.M.Titterington and the reviewers for their critical reading of the manuscript and helpful comments. This work was supported in part by the Israeli Ministry of Science and Technology under contract number 3528, and in part by the Paul Ivanier Center for Robotics and Production Management, Ben Gurion University of the Negev, Israel.",

year = "1997",

month = dec,

day = "1",

doi = "10.1109/34.574805",

language = "English",

volume = "19",

pages = "187--192",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "Institute of Electrical and Electronics Engineers",

number = "2",

}

TY - JOUR

T1 - Linear discriminant analysis for two classes via removal of classification structure

AU - Aladjem, Mayer

N1 - Funding Information: The author wishes to thank associate editor Prof. D.M.Titterington and the reviewers for their critical reading of the manuscript and helpful comments. This work was supported in part by the Israeli Ministry of Science and Technology under contract number 3528, and in part by the Paul Ivanier Center for Robotics and Production Management, Ben Gurion University of the Negev, Israel.

PY - 1997/12/1

Y1 - 1997/12/1

N2 - A new method for two-class linear discriminant analysis, called "removal of classification structure," is proposed. Its novelty lies in the transformation of the data along an identified discriminant direction into data without discriminant information and iteration to obtain the next discriminant direction. It is free to search for discriminant directions oblique to each other and ensures that the informative directions already found will not be chosen again at a later stage. The efficacy of the method is examined for two discriminant criteria. Studies with a wide spectrum of synthetic data sets and a real data set indicate that the discrimination quality of these criteria can be improved by the proposed method.

AB - A new method for two-class linear discriminant analysis, called "removal of classification structure," is proposed. Its novelty lies in the transformation of the data along an identified discriminant direction into data without discriminant information and iteration to obtain the next discriminant direction. It is free to search for discriminant directions oblique to each other and ensures that the informative directions already found will not be chosen again at a later stage. The efficacy of the method is examined for two discriminant criteria. Studies with a wide spectrum of synthetic data sets and a real data set indicate that the discrimination quality of these criteria can be improved by the proposed method.

KW - Dimension reduction

KW - Discriminant plots

KW - Exploratory data analysis

KW - Linear discriminant analysis

KW - Structure removal

UR - http://www.scopus.com/inward/record.url?scp=0031077975&partnerID=8YFLogxK

U2 - 10.1109/34.574805

DO - 10.1109/34.574805

M3 - Article

AN - SCOPUS:0031077975

SN - 0162-8828

VL - 19

SP - 187

EP - 192

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 2

ER -

Linear discriminant analysis for two classes via removal of classification structure

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this