Premium
Application of Fuzzy Logic and Near Infrared Spectroscopy for Malt Quality Evaluation
Author(s) -
Nielsen J. P.,
Bro R.,
Larsen J.,
Munck L.
Publication year - 2002
Publication title -
journal of the institute of brewing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.523
H-Index - 51
eISSN - 2050-0416
pISSN - 0046-9750
DOI - 10.1002/j.2050-0416.2002.tb00574.x
Subject(s) - fuzzy logic , quality (philosophy) , data mining , set (abstract data type) , computer science , univariate , index (typography) , mathematics , artificial intelligence , machine learning , multivariate statistics , physics , world wide web , programming language , quantum mechanics
An increasing number of quality criteria are involved in the evaluation of the final malt. This implies a comprehensive quality evaluation, normally based on experience and prior knowledge by the maltster/brewer/breeder. This paper describes the principle in, and use of, fuzzy logic for the translation of a complex malt quality profile into a simple univariate overall quality index (OQI). The approach was tested on a data set of 50 malt samples including eleven quality parameters according to the European Brewery Convention. The presented fuzzy logic approach involves three steps: i) an appropriate definition of how good a certain quality parameter level is, ii) a sound way to combine several quality parameters and iii) a way to express the overall quality based on all these individual parameters, taking their individual relative importance into account. The fuzzy logic based OQI presented here turned out to be a sound index for the overall quality of the tested malt samples, and thus provides a way of reducing and automating the quality data evaluation. It is furthermore shown that near infrared transmittance spectra of the malt samples showed reasonable ability to predict the calculated OQI. Hereby, both analysis and evaluation efforts in malting barley breeding can be reduced considerably.