Using data mining techniques to predict industrial wine problem fermentations

Urtubia, Alejandra; Pérez-Correa, José Ricardo; Soto, Álvaro; Pszczólkowski, Philippo

doi:10.1016/j.foodcont.2006.09.010

Cited by 44 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There exist two groups of models for the wine fermentation process; the first type focuses on the predictability and the second type on interpretability. By means of data mining techniques like decision trees, machine learning, support vector machines or neural networks ( [29], [30], [33] and [32]), the first type of models exploit advances in computing technologies and large databases to predict fermentation profiles. These types of models have the advantage of including a large quantity of factors of the process, but they lack biological, physical or mechanical foundations and generally they are complex and difficult to interpret.…”

Section: Introductionmentioning

confidence: 99%

Reconciling Competing Models: A Case Study of Wine Fermentation Kinetics

Assar

Vargas

Sherman

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Mathematical models of wine fermentation kinetics promise early diagnosis of stuck or sluggish winemaking processes as well as better matching of industrial yeast strains to specific vineyards. The economic impact of these challenges is significant: worldwide losses from stuck or sluggish fermentations are estimated at 7 billion A C annually, and yeast starter production is a highly competitive market estimated at 40 million A C annually. Additionally, mathematical models are an important tool for studying the biology of wine yeast fermentation through functional genomics, and contribute to our understanding of the link between genotype and phenotype for these important cell factories.Here, we have developed an accurate combined model that best matches experimental observations over a wide range of initial conditions. This model is based on mathematical analysis of three competing ODE models for wine fermentation kinetics and statistical comparison of their predictions with a large set of experimental data. By classifying initial conditions into qualitative intervals and by systematically evaluating the competing models, we provide insight into the strengths and weaknesses of the existing models, and identify the key elements of their symbolic representation that most influence the accuracy of their predictions. In particular, we can make a distinction between main effects that are linear in the modeled variable, and secondary quadratic effects that model interactions between cellular processes.We generalize our methodology to the common case where one wishes to combine existing, competing models and refine them to better agree with experimental data. The first step is symbolic, and rewrites each model into a polynomial form in which main and secondary effects can be conveniently expressed. The second step is statistical, classifying the match of each model's predictions with experimental data, and identifying the key terms in its equations. Finally, we use a combination of those terms and their coefficients to instantiate the combined model expressed in polynomial form. We show that this procedure is feasible for the case of wine fermentation kinetics, allowing predictions which closely match experimental observations in normal and problematic fermentation.

show abstract

Section: Introductionmentioning

confidence: 99%

Reconciling Competing Models: A Case Study of Wine Fermentation Kinetics

Assar

Vargas

Sherman

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Specifically in wine, statistical approaches have been applied for discriminating between different wine varieties [9], and only few studies for monitoring wine fermentations [10] and detection of abnormal behaviors [11][12][13]. However, PLS and PCA are linear in nature whereas many processes-such as winemaking-exhibit non-linear relations between the process parameters and the quality parameters [14].…”

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

“…Some statistical studies have been developed for fault detection and diagnosis in batch and fed-batch processes. Methods of multivariate statistics, such as multiway principal component analysis (MPCA), multiway partial least squares (MPLS), parallel factor analysis (PARAFAC) and Mean Hypothesis Testing, have been tested [6][7][8][9][10][11] [12][13][14]. However, and since PCA does not use class information, LDA usually outperforms PCA for pattern classification [15].…”

Section: Introductionmentioning

confidence: 99%

Predictive power of LDA to discriminate abnormal wine fermentations

Urtubia

Roger

2011

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

Wine fermentation is a critical step of winemaking. Unfavorable conditions can seriously affect the quality of the final product; however, it is difficult to anticipate these abnormal behaviors. In this study, the predictive power of stepwise linear discriminant analysis (SLDA) was evaluated to discriminate the behavior of wine fermentation. Information on different chemical concentrations from 18 industrial wine fermentations of Cabernet Sauvignon was used in this study. The statistical procedure consisted of curve fitting with exponential curve, and Stepwise LDA applied to the parameters of the curve. This methodology was applied to different times between the beginning and the end of fermentation (72, 95, 100, 150, 200 and 400 h). The results revealed that between seven and eight, of the 28 variables studied, minimized the Standard Error of Cross-Validation (SECV) for the different times. In almost all times studied, correlation coefficient of alcoholic degree, initial concentration of glucose, initial density and correlation coefficient of tartaric acid were the variables more discriminant, and they indicated some differences between a normal and an abnormal fermentation, which need to be corroborated with more information. In this work, before 95 h, it was not possible to minimize the prediction error and find the most discriminant variables.

show abstract

Using data mining techniques to predict industrial wine problem fermentations

Cited by 44 publications

References 16 publications

Reconciling Competing Models: A Case Study of Wine Fermentation Kinetics

Reconciling Competing Models: A Case Study of Wine Fermentation Kinetics

Prediction of problematic wine fermentations using artificial neural networks

Predictive power of LDA to discriminate abnormal wine fermentations

Contact Info

Product

Resources

About