<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In order to explore the applicability of random forest algorithm in the detection of alcoholic foreign matter and to improve the identification of alcoholic products. In this paper, based on the random forest algorithm, the feature values of random forest are fuzzified using the fuzzy comprehensive evaluation method, and the application model of alcohol foreign body detection anomaly based on random forest fuzzy tree nodes is established. And the reliability of the random forest algorithm is verified by the quantitative analysis of the three test indexes (i.e., recall, precision, and accuracy) and the anomaly proportion coefficient of the test data set by the algorithm in this paper. The results show that the recall, precision, and accuracy of the random forest-based anomaly detection for alcoholic beverage foreign objects are 99.65%, 95.49%, and 97.19%, respectively, and the average value of the three eigenvalues of this paper’s algorithm is 97.44%, which is 59.89%, 43.98%, and 1.92% higher than the other three algorithms, respectively. In terms of the anomaly proportion coefficient, the stability of the algorithm in this paper is the best when the coefficient takes values between [0.2, 0.6]. It can be shown that the algorithm based on random forest can be applied to the foreign matter detection of wine, and through the detection of anomalies, the quality of the wine currently undergoing detection can be clearly and explicitly analyzed, which also provides a new direction for the application of the random forest algorithm.</p>
</abstract>

In order to explore the applicability of random forest algorithm in the detection of alcoholic foreign matter and to improve the identification of alcoholic products. In this paper, based on the random forest algorithm, the feature values of random forest are fuzzified using the fuzzy comprehensive evaluation method, and the application model of alcohol foreign body detection anomaly based on random forest fuzzy tree nodes is established. And the reliability of the random forest algorithm is verified by the quantitative analysis of the three test indexes (i.e., recall, precision, and accuracy) and the anomaly proportion coefficient of the test data set by the algorithm in this paper. The results show that the recall, precision, and accuracy of the random forest-based anomaly detection for alcoholic beverage foreign objects are 99.65%, 95.49%, and 97.19%, respectively, and the average value of the three eigenvalues of this paper’s algorithm is 97.44%, which is 59.89%, 43.98%, and 1.92% higher than the other three algorithms, respectively. In terms of the anomaly proportion coefficient, the stability of the algorithm in this paper is the best when the coefficient takes values between [0.2, 0.6]. It can be shown that the algorithm based on random forest can be applied to the foreign matter detection of wine, and through the detection of anomalies, the quality of the wine currently undergoing detection can be clearly and explicitly analyzed, which also provides a new direction for the application of the random forest algorithm.

Application of random forest algorithm in the detection of foreign objects in wine

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In order to explore the applicability of random forest algorithm in the detection of alcoholic foreign matter and to improve the identification of alcoholic...

Application of random forest algorithm in the detection of foreign objects in wine

Publié en ligne: 19 juil. 2023

Pages: -

Reçu: 16 mars 2022

Accepté: 28 nov. 2022

DOI: https://doi.org/10.2478/amns.2023.2.00055

Mots clés
Random forest algorithm, Wine foreign body detection, Fuzzy comprehensive judgment method, Anomaly proportion coefficient, Quantitative analysis

© 2023 Liangbo Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Application of random forest algorithm in the detection of foreign objects in wine

Publié en ligne: 19 juil. 2023

Pages: -

Reçu: 16 mars 2022

Accepté: 28 nov. 2022

DOI: https://doi.org/10.2478/amns.2023.2.00055

Mots clésRandom forest algorithm, Wine foreign body detection, Fuzzy comprehensive judgment method, Anomaly proportion coefficient, Quantitative analysis

© 2023 Liangbo Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Random forest algorithm, Wine foreign body detection, Fuzzy comprehensive judgment method, Anomaly proportion coefficient, Quantitative analysis