Classification of Slovak white wines using artificial neural networks and discriminant techniques

Kružlicová, Dáša; Mocák, Ján; Balla, Branko; Pet'ka, Ján; Farková, Marta; Havel, Josef

doi:10.1016/j.foodchem.2008.06.047

Cited by 72 publications

(38 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…From the 19 variables studied, the statistical method Stepwise Linear Discriminant Analysis (SLDA) selected 10 variables and gave a global percentage of correct classification of 98.8 and 97.3% of correct prediction; the ANN method, however, selected seven variables which gave a correct classification for training and a prediction of 100%. The multilayer perceptron technique was applied to classify 36 Slovak wine samples of three varieties, produced by four producers in three different years with respect to the following variables: variety, producer/location and the year of production [26]. Over the samples considered, a prediction performance of at least 93.3% was obtained.…”

Section: Introductionmentioning

confidence: 99%

Prediction of problematic wine fermentations using artificial neural networks

Román

Hernández

Urtubia

2011

Bioprocess Biosyst Eng

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have been used for the recognition of non-linear patterns, a characteristic of bioprocesses like wine production. In this work, ANNs were tested to predict problems of wine fermentation. A database of about 20,000 data from industrial fermentations of Cabernet Sauvignon and 33 variables was used. Two different ways of inputting data into the model were studied, by points and by fermentation. Additionally, different sub-cases were studied by varying the predictor variables (total sugar, alcohol, glycerol, density, organic acids and nitrogen compounds) and the time of fermentation (72, 96 and 256 h). The input of data by fermentations gave better results than the input of data by points. In fact, it was possible to predict 100% of normal and problematic fermentations using three predictor variables: sugars, density and alcohol at 72 h (3 days). Overall, ANNs were capable of obtaining 80% of prediction using only one predictor variable at 72 h; however, it is recommended to add more fermentations to confirm this promising result.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of problematic wine fermentations using artificial neural networks

Román

Hernández

Urtubia

2011

Bioprocess Biosyst Eng

View full text Add to dashboard Cite

show abstract

“…Currently, wine is often classified according to polyphenolic compounds, volatile compounds, minerals, and trace elements using high-performance liquid chromatography (HPLC) (Beltran et al 2006), gas chromatographymass spectroscopy (GC-MS) (Kruzlicova et al 2009), electronic nose (Aleixandre et al 2008), atomic absorption spectroscopy (AAS) (Galgano et al 2008) and etc. These techniques are precise enough to guarantee the authenticity of wine.…”

Section: Introductionmentioning

confidence: 99%

Discrimination Between Shaoxing Wines and Other Chinese Rice Wines by Near-Infrared Spectroscopy and Chemometrics

Shen

Yang

Ying

et al. 2010

Food Bioprocess Technol

View full text Add to dashboard Cite

Shaoxing rice wine (also called Shaoxing wine) is the most well-known Chinese rice wine in China. The common fraudulent practice in the commercialization of Chinese rice wine is to sell wines from different geographical origins under the denomination of Shaoxing rice wine. In this study, the use of near-infrared (NIR) spectroscopy combined with chemometrics as a rapid tool for the discrimination of Chinese rice wine from three geographical origins ("Fujian", "non-Shaoxing", "Shaoxing") has been preliminarily investigated. NIR spectra were collected in transmission mode in the wavelength range of 800-2,500 nm. Discriminant models were developed by principal component analysis (PCA), discriminant analysis (DA), and discriminant partial least-squares analysis (DPLS). The chemical properties of Chinese rice wine were also investigated to find out the difference between samples from three varied origins. The results showed that good classification could be obtained after spectral pre-treatment. The percentage of samples correctly classified by both DA and DPLS methods in calibration and validation set was 97.2% and 100%, respectively. The results demonstrated that NIR could be used as a simple and rapid technique to distinguish Shaoxing wines from non-Shaoxing wines and Fujian wines. To further validate the ability of NIR spectroscopy, more samples should be incorporated to build a more robust model.

show abstract

“…Alternative methods to analyse sensory attributes are therefore desirable. Aroma is one important characteristic of wine and there have been several recent attempts to analyse aroma characteristics of wine by gas chromatography mass spectrometry (GCMS) and chemometric analysis (Canuti et al, 2009;Cozzolino et al, 2008;Kruzlicova et al, 2009;Louw et al, 2009;Masson & Schneider, 2009). GCMS is well suited to volatile analysis and can give insight into aroma characteristics of wine.…”

Section: Introductionmentioning

confidence: 99%