مدل سازی تنظیمات نوشیدنی به وسیله داده کاوی از خواص های فیزیکی
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|22172||2009||7 صفحه PDF||سفارش دهید||5922 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Decision Support Systems, Volume 47, Issue 4, November 2009, Pages 547–553
We propose a data mining approach to predict human wine taste preferences that is based on easily available analytical tests at the certification step. A large dataset (when compared to other studies in this domain) is considered, with white and red vinho verde samples (from Portugal). Three regression techniques were applied, under a computationally efficient procedure that performs simultaneous variable and model selection. The support vector machine achieved promising results, outperforming the multiple regression and neural network methods. Such model is useful to support the oenologist wine tasting evaluations and improve wine production. Furthermore, similar techniques can help in target marketing by modeling consumer tastes from niche markets.
Once viewed as a luxury good, nowadays wine is increasingly enjoyed by a wider range of consumers. Portugal is a top ten wine exporting country, with 3.17% of the market share in 2005 . Exports of its vinho verde wine (from the northwest region) have increased by 36% from 1997 to 2007 . To support its growth, the wine industry is investing in new technologies for both wine making and selling processes. Wine certification and quality assessment are key elements within this context. Certification prevents the illegal adulteration of wines (to safeguard human health) and assures quality for the wine market. Quality evaluation is often part of the certification process and can be used to improve wine making (by identifying the most influential factors) and to stratify wines such as premium brands (useful for setting prices). Wine certification is generally assessed by physicochemical and sensory tests . Physicochemical laboratory tests routinely used to characterize wine include determination of density, alcohol or pH values, while sensory tests rely mainly on human experts. It should be stressed that taste is the least understood of the human senses  thus wine classification is a difficult task. Moreover, the relationships between the physicochemical and sensory analysis are complex and still not fully understood . Advances in information technologies have made it possible to collect, store and process massive, often highly complex datasets. All this data hold valuable information such as trends and patterns, which can be used to improve decision making and optimize chances of success . Data mining (DM) techniques  aim at extracting high-level knowledge from raw data. There are several DM algorithms, each one with its own advantages. When modeling continuous data, the linear/multiple regression (MR) is the classic approach. The backpropagation algorithm was first introduced in 1974  and later popularized in 1986 . Since then, neural networks (NNs) have become increasingly used. More recently, support vector machines (SVMs) have also been proposed  and . Due to their higher flexibility and nonlinear learning capabilities, both NNs and SVMs are gaining an attention within the DM field, often attaining high predictive performances  and . SVMs present theoretical advantages over NNs, such as the absence of local minima in the learning phase. In effect, the SVM was recently considered one of the most influential DM algorithms . While the MR model is easier to interpret, it is still possible to extract knowledge from NNs and SVMs, given in terms of input variable importance  and . When applying these DM methods, variable and model selection are critical issues. Variable selection  is useful to discard irrelevant inputs, leading to simpler models that are easier to interpret and that usually give better performances. Complex models may overfit the data, losing the capability to generalize, while a model that is too simple will present limited learning capabilities. Indeed, both NN and SVM have hyperparameters that need to be adjusted , such as the number of NN hidden nodes or the SVM kernel parameter, in order to get good predictive accuracy (see Section 2.3). The use of decision support systems by the wine industry is mainly focused on the wine production phase . Despite the potential of DM techniques to predict wine quality based on physicochemical data, their use is rather scarce and mostly considers small datasets. For example, in 1991 the “Wine” dataset was donated into the UCI repository . The data contain 178 examples with measurements of 13 chemical constituents (e.g. alcohol, Mg) and the goal is to classify three cultivars from Italy. This dataset is very easy to discriminate and has been mainly used as a benchmark for new DM classifiers. In 1997 , a NN fed with 15 input variables (e.g. Zn and Mg levels) was used to predict six geographic wine origins. The data included 170 samples from Germany and a 100% predictive rate was reported. In 2001 , NNs were used to classify three sensory attributes (e.g. sweetness) of Californian wine, based on grape maturity levels and chemical analysis (e.g. titrable acidity). Only 36 examples were used and a 6% error was achieved. Several physicochemical parameters (e.g. alcohol, density) were used in  to characterize 56 samples of Italian wine. Yet, the authors argued that mapping these parameters with a sensory taste panel is a very difficult task and instead they used a NN fed with data taken from an electronic tongue. More recently, mineral characterization (e.g. Zn and Mg) was used to discriminate 54 samples into two red wine classes . A probabilistic NN was adopted, attaining 95% accuracy. As a powerful learning tool, SVM has outperformed NN in several applications, such as predicting meat preferences . Yet, in the field of wine quality only one application has been reported, where spectral measurements from 147 bottles were successfully used to predict 3 categories of rice wine age . In this paper, we present a case study for modeling taste preferences based on analytical data that are easily available at the wine certification step. Building such model is valuable not only for certification entities but also wine producers and even consumers. It can be used to support the oenologist's wine evaluations, potentially improving the quality and speed of their decisions. Moreover, measuring the impact of the physicochemical tests in the final wine quality is useful for improving the production process. Furthermore, it can help in target marketing , i.e. by applying similar techniques to model the consumer's preferences of niche and/or profitable markets. The main contributions of this work are: • We present a novel method that performs simultaneous variable and model selection for NN and SVM techniques. The variable selection is based on sensitivity analysis , which is a computationally efficient method that measures input relevance and guides the variable selection process. Also, we propose a parsimony search method to select the best SVM kernel parameter with a low computational effort. • We test such approach in a real-world application, the prediction of vinho verde wine (from the Minho region of Portugal) taste preferences, showing its impact in this domain. In contrast with previous studies, a large dataset is considered, with a total of 4898 white and 1599 red samples. Wine preferences are modeled under a regression approach, which preserves the order of the grades, and we show how the definition of the tolerance concept is useful for accessing different performance levels. We believe that this integrated approach is valuable to support applications where ranked sensory preferences are required, for example in wine or meat quality assurance. The paper is organized as follows: Section 2 presents the wine data, DM models and variable selection approach; in Section 3, the experimental design is described and the obtained results are analyzed; finally, conclusions are drawn in Section 4.
نتیجه گیری انگلیسی
In recent years, the interest in wine has increased, leading to growth of the wine industry. As a consequence, companies are investing in new technologies to improve wine production and selling. Quality certification is a crucial step for both processes and is currently largely dependent on wine tasting by human experts. This work aims at the prediction of wine preferences from objective analytical tests that are available at the certification step. A large dataset (with 4898 white and 1599 red entries) was considered, including vinho verde samples from the northwest region of Portugal. This case study was addressed by two regression tasks, where each wine type preference is modeled in a continuous scale, from 0 (very bad) to 10 (excellent). This approach preserves the order of the classes, allowing the evaluation of distinct accuracies, according to the degree of error tolerance (T) that is accepted. Due to advances in the data mining (DM) field, it is possible to extract knowledge from raw data. Indeed, powerful techniques such as neural networks (NNs) and more recently support vector machines (SVMs) are emerging. While being more flexible models (i.e. no a priori restriction is imposed), the performance depends on a correct setting of hyperparameters (e.g. number of hidden nodes of the NN architecture or SVM kernel parameter). On the other hand, the multiple regression (MR) is easier to interpret than NN/SVM, with most of the NN/SVM applications considering their models as black boxes. Another relevant aspect is variable selection, which leads to simpler models while often improving the predictive performance. In this study, we present an integrated and computationally efficient approach to deal with these issues. Sensitivity analysis is used to extract knowledge from the NN/SVM models, given in terms of relative importance of the inputs. Simultaneous variable and model selection scheme is also proposed, where the variable selection is guided by sensitivity analysis and the model selection is based on parsimony search that starts from a reasonable value and is stopped when the generalization estimate decreases. Encouraging results were achieved, with the SVM model providing the best performances, outperforming the NN and MR techniques, particularly for white vinho verde wine, which is the most common type. When admitting only the correct classified classes (T = 0.5), the overall accuracies are 62.4% (red) and 64.6% (white). It should be noted that the datasets contain six/seven classes (from 3 to 8/9). These accuracies are much better than the ones expected by a random classifier. The performance is substantially improved when the tolerance is set to accept responses that are correct within the one of the two nearest classes (T = 1.0), obtaining a global accuracy of 89.0% (red) and 86.8% (white). In particular, for both tasks the majority of the classes present an individual accuracy (precision) higher than 90%. The superiority of SVM over NN is probably due to the differences in the training phase. The SVM algorithm guarantees an optimum fit, while NN training may fall into a local minimum. Also, the SVM cost function (Fig. 2) gives a linear penalty to large errors. In contrast, the NN algorithm minimizes the sum of squared errors. Thus, the SVM is expected to be less sensitive to outliers and this effect results in a higher accuracy for low error tolerances. As argued in , it is difficult to compare DM methods in a fair way, with data analysts tending to favor models that they know better. We adopted the default suggestions of the R tool , except for the hyperparameters (which were set using a grid search). Since the default settings are more commonly used, this seems a reasonable assumption for the comparison. Nevertheless, different NN results could be achieved if different hidden node and/or minimization cost functions were used. Under the tested setup, the SVM algorithm provided the best results while requiring more computation. Yet, the SVM fitting can still be achieved within a reasonable time with current processors. For example, one run of the 5-fold cross-validation testing takes around 26 min for the larger white dataset, which covers a three-year collection period. The result of this work is important for the wine industry. At the certification phase and by Portuguese law, the sensory analysis has to be performed by human tasters. Yet, the evaluations are based in the experience and knowledge of the experts, which are prone to subjective factors. The proposed data-driven approach is based on objective tests and thus it can be integrated into a decision support system, aiding the speed and quality of the oenologist performance. For instance, the expert could repeat the tasting only if her/his grade is far from the one predicted by the DM model. In effect, within this domain the T = 1.0 distance is accepted as a good quality control process and, as shown in this study, high accuracies were achieved for this tolerance. The model could also be used to improve the training of oenology students. Furthermore, the relative importance of the inputs brought interesting insights regarding the impact of the analytical tests. Since some variables can be controlled in the production process this information can be used to improve the wine quality. For instance, alcohol concentration can be increased or decreased by monitoring the grape sugar concentration prior to the harvest. Also, the residual sugar in wine could be raised by suspending the sugar fermentation carried out by yeasts. Moreover, the volatile acidity produced during the malolactic fermentation in red wine depends on the lactic bacteria control activity. Another interesting application is target marketing . Specific consumer preferences from niche and/or profitable markets (e.g. for a particular country) could be measured during promotion campaigns (e.g. free wine tastings at supermarkets) and modeled using similar DM techniques, aiming at the design of brands that match these market needs.