TY  - JOUR
AU  - Pestorić, Mladenka
AU  - Mastilović, Jasna
AU  - Kevrešan, Žarko
AU  - Pezo, Lato
AU  - Belović, Miona
AU  - Glogovac, Svetlana
AU  - Škrobot, Dubravka
AU  - Ilić, Nebojša
AU  - Takač, Adam
PY  - 2021
UR  - http://fiver.ifvcns.rs/handle/123456789/2482
AB  - Sensory analysis is the best mean to precisely describe the eating quality of fresh foods. However, it is expensive and time-consuming method which cannot be used
for measuring quality properties in real time. The aim of this paper was to contribute to
the study of the relationship between sensory and instrumental data, and to define a proper model for predicting sensory properties of fresh tomato through the determination of the
physicochemical properties. Principal Component Analysis (PCA) was applied to the
experimental data to characterize and differentiate among the observed genotypes, explaining 73.52% of the total variance, using the first three principal components.
Artificial neural network (ANN) model was used for the prediction of sensory properties
based on the results obtained by basic chemical and instrumental determinations. The
developed ANN model predicts the sensory properties with high adequacy, with the
overall coefficient of determination of 0.859.
AB  - Senzorska analiza predstavlja najbolje sredstvo za precizno opisivanje kvaliteta svežih namirnica. Međutim,to je skupa i dugotrajna metoda koja se ne može koristiti za merenje pokazatelja kvaliteta u realnom vremenu. Cilj ovog rada bio je da doprinese proučavanju odnosa između podataka dobijenih primenom senzorske analize i instrumentalnih metoda i da definiše odgovarajući model za predviđanje senzorskih svojstava svežeg paradajza pomoću određivanja fizičko-hemijskih svojstava. Analiza glavnih komponenti (RSA) primenjena je na eksperimentalne podatke da bi se okarakterisali i diferencirali posmatrani genotipovi, objašnjavajući 73,52% od ukupne varijanse, koristeći prve tri glavne komponente. Model veštačke neuronske mreže (ANN) korišćen je za predviđanje senzorskih svojstava na osnovu rezultata dobijenih osnovnim hemijskim i instrumentalnim određivanjima. Razvijeni ANN model predviđa senzorska svojstva sa visokom adekvatnošću, sa ukupnim koeficijentom determinacije od 0,859.
PB  - Novi Sad : University of Novi Sad, Institute of Food Technology
T2  - Food and Feed Research
T1  - Artificial neural network model in predicting the quality of fresh tomato genotypes
T1  - Veštačke neuronske mreže za predviđanje kvaliteta različitih genotipova paradajza
EP  - 21
IS  - 1
SP  - 9
VL  - 48
DO  - 10.5937/ffr48-29661
ER  - 

@article{
author = "Pestorić, Mladenka and Mastilović, Jasna and Kevrešan, Žarko and Pezo, Lato and Belović, Miona and Glogovac, Svetlana and Škrobot, Dubravka and Ilić, Nebojša and Takač, Adam",
year = "2021",
abstract = "Sensory analysis is the best mean to precisely describe the eating quality of fresh foods. However, it is expensive and time-consuming method which cannot be used
for measuring quality properties in real time. The aim of this paper was to contribute to
the study of the relationship between sensory and instrumental data, and to define a proper model for predicting sensory properties of fresh tomato through the determination of the
physicochemical properties. Principal Component Analysis (PCA) was applied to the
experimental data to characterize and differentiate among the observed genotypes, explaining 73.52% of the total variance, using the first three principal components.
Artificial neural network (ANN) model was used for the prediction of sensory properties
based on the results obtained by basic chemical and instrumental determinations. The
developed ANN model predicts the sensory properties with high adequacy, with the
overall coefficient of determination of 0.859., Senzorska analiza predstavlja najbolje sredstvo za precizno opisivanje kvaliteta svežih namirnica. Međutim,to je skupa i dugotrajna metoda koja se ne može koristiti za merenje pokazatelja kvaliteta u realnom vremenu. Cilj ovog rada bio je da doprinese proučavanju odnosa između podataka dobijenih primenom senzorske analize i instrumentalnih metoda i da definiše odgovarajući model za predviđanje senzorskih svojstava svežeg paradajza pomoću određivanja fizičko-hemijskih svojstava. Analiza glavnih komponenti (RSA) primenjena je na eksperimentalne podatke da bi se okarakterisali i diferencirali posmatrani genotipovi, objašnjavajući 73,52% od ukupne varijanse, koristeći prve tri glavne komponente. Model veštačke neuronske mreže (ANN) korišćen je za predviđanje senzorskih svojstava na osnovu rezultata dobijenih osnovnim hemijskim i instrumentalnim određivanjima. Razvijeni ANN model predviđa senzorska svojstva sa visokom adekvatnošću, sa ukupnim koeficijentom determinacije od 0,859.",
publisher = "Novi Sad : University of Novi Sad, Institute of Food Technology",
journal = "Food and Feed Research",
title = "Artificial neural network model in predicting the quality of fresh tomato genotypes, Veštačke neuronske mreže za predviđanje kvaliteta različitih genotipova paradajza",
pages = "21-9",
number = "1",
volume = "48",
doi = "10.5937/ffr48-29661"
}

Pestorić, M., Mastilović, J., Kevrešan, Ž., Pezo, L., Belović, M., Glogovac, S., Škrobot, D., Ilić, N.,& Takač, A.. (2021). Artificial neural network model in predicting the quality of fresh tomato genotypes. in Food and Feed Research
Novi Sad : University of Novi Sad, Institute of Food Technology., 48(1), 9-21.
https://doi.org/10.5937/ffr48-29661

Pestorić M, Mastilović J, Kevrešan Ž, Pezo L, Belović M, Glogovac S, Škrobot D, Ilić N, Takač A. Artificial neural network model in predicting the quality of fresh tomato genotypes. in Food and Feed Research. 2021;48(1):9-21.
doi:10.5937/ffr48-29661 .

Pestorić, Mladenka, Mastilović, Jasna, Kevrešan, Žarko, Pezo, Lato, Belović, Miona, Glogovac, Svetlana, Škrobot, Dubravka, Ilić, Nebojša, Takač, Adam, "Artificial neural network model in predicting the quality of fresh tomato genotypes" in Food and Feed Research, 48, no. 1 (2021):9-21,
https://doi.org/10.5937/ffr48-29661 . .