An Expert System for an Innovative Discrimination Tool of Commercial Table Grapes
Table grapes classification is an important task in the global market because of the interest of consumers to quality of foodstuff. Objective: an expert and innovative tool, based on several robust classifiers, was designed and implemented to achieve unequivocal criteria and support decision for the discrimination of table grapes. Materials: data are acquired by powerful analytical techniques such as Nuclear Magnetic Resonance (NMR) and are related to 5 attributes: production year, vineyard location, variety, use of plant growth regulators (PGRs) and application of trunk girdling. In particular, datasets consisting of 813 samples regarded the former 3 attributes while datasets based on 596 samples regarded the latter 2 ones. Methods: in absence of an a-priori knowledge, we addressed the problem as an inferential task and then adopted supervised approaches like error back propagation neural networks, trees and random forest classifiers able to manage information from training sets. Experimental Results and Conclusion: our study has shown that the three classifiers, especially that based on a supervised neural network, when applied to NMR data, give from good to excellent performances, depending on the attribute. Such performances pave the way to development of innovative tools for classification of table grapes.
Keywordsartificial neural networks J48 classifier random forest table grapes nuclear magnetic resonance metabolomics
Unable to display preview. Download preview PDF.
- 1.Official web site of EC, http://ec.europa.eu/agriculture/quality
- 2.Gallo, V., Mastrorilli, P., Cafagna, I., Nitti, G.I., Latronico, M., Romito, V.A., Minoja, A.P., Napoli, C., Longobardi, F., Schäfer, H., Schütz, B., Spraul, M.: Multivariate statistical analysis of 1H NMR data for evaluation of metabolic profile in commercial table grapes (Vitis vinifera): inter- vs intra-vineyard variability (submitted, 2012)Google Scholar
- 3.Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. (1998)Google Scholar
- 5.Menolascina, F., Tommasi, S., Paradiso, A., Cortellino, M., Bevilacqua, V., Mastronardi, G.: Novel Data Mining Techniques in aCGH based Breast Cancer Subtypes Profiling: the Biological Perspective. In: CIBCB, pp. 9–16 (2007)Google Scholar
- 7.Caruana, R., Niculescu-Mizil, A.: An Empirical Comparison of Supervised Learning Algorithms. In: ICML 2006 Proceedings of the 23rd International Conference on Machine Learning (2006)Google Scholar
- 8.Sachs, R.M., Weaver, R.J.: Gibberellin and Auxin-induced Berry Enlargement in Vitisvinifera L. J. Hort. Sci. 43, 185–195 (1968)Google Scholar
- 9.Yahuaca, J.B., Martínez-Peniche, R., Mader, E., Reyes, J.L.: Effects of Ethephon and Gird-ling on Firmness of “Red Malaga” Table Grape. Acta Hort. 565, 121–124 (2001)Google Scholar
- 11.Peppi, M.C., Fidelibus, M.W.: Effects of Forchlorfenuron and Abscisic Acid on The Quality of ‘Flame seedless’. Grapes HortScience 43, 173–176 (2008)Google Scholar
- 13.Quinlan, J.R.: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)Google Scholar