Classification of aged wine distillates using fuzzy and neural network systems

Raptis, CG; Siettos, CI; Kiranoudis, CT; Bafas, GV

dc.contributor.author	Raptis, CG	en
dc.contributor.author	Siettos, CI	en
dc.contributor.author	Kiranoudis, CT	en
dc.contributor.author	Bafas, GV	en
dc.date.accessioned	2014-03-01T01:15:30Z
dc.date.available	2014-03-01T01:15:30Z
dc.date.issued	2000	en
dc.identifier.issn	0260-8774	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13551
dc.subject	Back Propagation	en
dc.subject	Classification System	en
dc.subject	Fuzzy Classifier	en
dc.subject	Fuzzy Logic	en
dc.subject	Mathematical Model	en
dc.subject	Multi Criteria Decision Making	en
dc.subject	Neural System	en
dc.subject	Expert System	en
dc.subject	Neural Network	en
dc.subject.classification	Engineering, Chemical	en
dc.subject.classification	Food Science & Technology	en
dc.subject.other	MODEL	en
dc.title	Classification of aged wine distillates using fuzzy and neural network systems	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0260-8774(00)00087-X	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0260-8774(00)00087-X	en
heal.language	English	en
heal.publicationDate	2000	en
heal.abstract	The classification of aged wine distillates is a non-linear, multi-criteria decision-making problem characterized by overwhelming complexity, non-linearity and lack of objective information regarding the desired final product qualitative characteristics. The most efficient solution for the evaluation of aged wine distillates estimations with emphasis on the properties of the aroma and the taste, when an appropriate mathematical model cannot be found, is to develop adequate and reliable expert systems based on fuzzy logic and neural networks. A fuzzy classifier and a neural network are proposed for the classification of wine distillates for each of two distinct features of the products namely the aroma and the taste. The fuzzy classifier is based on the fuzzy k-nn algorithm while the neural system is a feedforward sigmoidal multilayer network which is trained using the back-propagation method. The results show that both fuzzy and neural classification systems performed remarkably well in the evaluation of the aroma and the taste of the products. (C) 2000 Elsevier Science Ltd. All rights reserved.	en
heal.publisher	ELSEVIER SCI LTD	en
heal.journalName	JOURNAL OF FOOD ENGINEERING	en
dc.identifier.doi	10.1016/S0260-8774(00)00087-X	en
dc.identifier.isi	ISI:000089796300007	en
dc.identifier.volume	46	en
dc.identifier.issue	4	en
dc.identifier.spage	267	en
dc.identifier.epage	275	en