Element selection and concentration analysis for classifying South America wine samples according to the country of origin Event as iCalendar

(Graduate School of Management)

28 November 2018

10 - 11am

Venue: The University of Auckland Business School, Level 3, Room 317, 12 Grafton Road, Auckland, 1010

Presenter: Dr Michel Anzanello, UFRGS (Universidade Federal do Rio Grande do Sul)

The talk will detail an approach for selecting the most informative features aimed at classifying wines samples according to the country of origin. The method relies on Kruskal-Wallis non-parametric test to remove non significant features, and Linear Discriminant Analysis to derive a feature importance index. The ranked features according that index are iteratively added to a subset and classification performance is assessed after each insertion. The number of selected features is chosen according the maximum accuracy in a repeated 10-fold cross-validation. Aiming at improving categorization accuracy, different classification techniques are tested. When applied to a wine dataset comprised of 53 samples from four South America countries (Argentina, Brazil, Chile, and Uruguay) and 45 chemical elements concentrations determined by ICP-OES and ICP-MS, the proposed framework yielded average 99.9% accurate classifications in the testing set, and retained average 6.73 of the 45 original elements. Retained chemical elements were then qualitatively assessed.

Professor Michel J Anzanello holds a PhD in Industrial and Systems Engineering from Rutgers University, USA (2009). He is a Professor at the Industrial Engineering (IE) Department of the Federal University of Rio Grande do Sul (UFRGS). His main research interests include data mining, multivariate analysis, quantitative methods in production control, and learning curve modeling. He received the 2017 Best Track Paper Award IEOM Conference. His research has been published in Computers and Electronic in Agriculture, Chemometrics and Intelligent Laboratory Systems,  International Journal of Production Economics, and Journal of Pharmaceutical and Biomedical Analysis, among others. His h-index is 11 (Scopus, 2018).

For more information contact:
Karin Olesen
Email: k.olesen@auckland.ac.nz
Ext. 87145