Premium
Discrimination by means of components that are orthogonal in the data space
Author(s) -
Kiers Henk A. L.
Publication year - 1997
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/(sici)1099-128x(199711/12)11:6<533::aid-cem493>3.0.co;2-1
Subject(s) - chemometrics , pattern recognition (psychology) , principal component analysis , computer science , mathematics , component (thermodynamics) , contrast (vision) , orthogonal array , component analysis , multidimensional data , orthographic projection , linear discriminant analysis , artificial intelligence , space (punctuation) , algorithm , statistics , data mining , machine learning , taguchi methods , physics , thermodynamics , operating system
Krzanowski ( J. Chemometrics , 9 , 509 (1995)) proposed a method for obtaining so‐called orthogonal canonical variates (henceforth called components) for discrimination purposes. In contrast with ordinary discriminant analysis, this method employs components that are orthogonal in the original data space. These components are derived in a successive way, thus optimizing discrimination of a component given the previously extracted components. Two alternative procedures are proposed to extract the desired number of components simultaneously, yielding a better overall discrimination. The simultaneous approaches are applied to the same two data sets as analysed by Krzanowski, as well as to Anderson's Iris data, and a comparison of discriminatory quality of the solutions is presented. © 1997 John Wiley & Sons, Ltd.