Direct and two-stage data analysis procedures based on PCA, PLS-DA and ANN for ISE-based electronic tongue-Effect of supervised feature extraction

P Ciosek; Z Brzózka; W Wróblewski; E Martinelli; C Di Natale; A D'Amico

doi:10.1016/j.talanta.2005.03.006

Direct and two-stage data analysis procedures based on PCA, PLS-DA and ANN for ISE-based electronic tongue-Effect of supervised feature extraction

Talanta. 2005 Sep 15;67(3):590-6. doi: 10.1016/j.talanta.2005.03.006. Epub 2005 Apr 14.

Authors

P Ciosek¹, Z Brzózka, W Wróblewski, E Martinelli, C Di Natale, A D'Amico

Affiliation

¹ Department of Analytical Chemistry, Warsaw University of Technology, Noakowskiego 3, 00-664 Warsaw, Poland.

PMID: 18970211
DOI: 10.1016/j.talanta.2005.03.006

Abstract

A novel strategy of data analysis for artificial taste and odour systems is presented in this work. It is demonstrated that using a supervised method also in feature extraction phase enhances fruit juice classification capability of sensor array developed at Warsaw University of Technology. Comparison of direct processing (raw data processed by Artificial Neural Network (ANN), raw data processed by Partial Least Squares-Discriminant Analysis (PLS-DA)) and two-stage processing (Principal Components Analysis (PCA) outputs processed by ANN, PLS-DA outputs processed by ANN) is presented. It is shown that considerable increase of classification capability occurred in the case of the new method proposed by the authors.