REGULARIZED DISCRIMINANT-ANALYSIS (RDA) - MODELING FOR THE BINARY DISCRIMINATION BETWEEN POLLUTION TYPES

Authors
BALDOVIN A WEN W MASSART DL TURELLO A
Citation
A. Baldovin et al., REGULARIZED DISCRIMINANT-ANALYSIS (RDA) - MODELING FOR THE BINARY DISCRIMINATION BETWEEN POLLUTION TYPES, Chemometrics and intelligent laboratory systems, 38(1), 1997, pp. 25-37
Citations number
21
Categorie Soggetti
Computer Application, Chemistry & Engineering","Instument & Instrumentation","Chemistry Analytical","Computer Science Artificial Intelligence","Robotics & Automatic Control
Journal title
Chemometrics and intelligent laboratory systems → ACNP
ISSN journal
01697439
Volume
38
Issue
1
Year of publication
1997
Pages
25 - 37
Database
ISI
SICI code
0169-7439(1997)38:1<25:RD(-MF>2.0.ZU;2-T
Abstract
Discrimination between different types of pollution is carried out wit h RDA. A description of the most important characteristics of the mode l is presented. Attention is paid to the four extreme discrimination m odels that are special cases of RDA and which are the well known linea r discriminant analysis (LDA) and quadratic discriminant analysis (QDA ), the nearest-means classifier (NM) and the weighted nearest means-cl assifier (WNM). A comparison among RDA and partial least squares (PLS) is attempted and some first considerations are proposed. Feature sele ction to determine the most important variables for the discrimination is studied. (C) 1997 Elsevier Science B.V.