INQUISUR   21779
INSTITUTO DE QUIMICA DEL SUR
Unidad Ejecutora - UE
artículos
Título:
TWO-DIMENSIONAL LINEAR DISCRIMINANT ANALYSIS FOR CLASSIFICATION OF THREE-WAY CHEMICAL DATA
Autor/es:
MATÍAS INSAUSTI; MARIO CESAR UGULINO DE ARAUJO; SÓFACLES FIGUEREDO CARREIROSOARES; BEATRIZ S. FERNANDEZ BAND; ADENILTON C. DA SILVA; ROBERTO K. GALVÃO
Revista:
ANALYTICA CHIMICA ACTA
Editorial:
ELSEVIER SCIENCE BV
Referencias:
Lugar: Amsterdam; Año: 2016 vol. 938 p. 53 - 62
ISSN:
0003-2670
Resumen:
The two-dimensional linear discriminant analysis (2D-LDA) algorithm was originally proposed in thecontext of face image processing for the extraction of features with maximal discriminant power.However, despite its promising performance in image processing tasks, the 2D-LDA algorithm has not yetbeen used in applications involving chemical data. The present paper bridges this gap by investigatingthe use of 2D-LDA in classification problems involving three-way spectral data. The investigation wasconcerned with simulated data, as well as real-life data sets involving the classification of dry-curedParma ham according to ageing by surface autofluorescence spectrometry and the classification ofedible vegetable oils according to feedstock using total synchronous fluorescence spectrometry. Theresults were compared with those obtained by using the spectral data with no feature extraction, U-PLSDA(Partial Least Squares Discriminant Analysis applied to the unfolded data), and LDA employingTUCKER-3 or PARAFAC scores. In the simulated data set, all methods yielded a correct classification rateof 100%. However, in the Parma ham and vegetable oil data sets, better classification rates were obtained