Classification of Red Wine Beverage Quality Using a Support Vector Machine Algorithm Based on Forward Selection as Feature Selection

Muhammad Azhar Luthfi, Ajib Susanto

Abstract


Wine is an alcoholic drink produced from the fermentation process of grapes or can use other types of fruit. Currently, the provision of wine quality certification uses physical tests and chemical tests. In this research, a machine learning technology approach was used to classify the quality of wine drinks. Support Vector Machine (SVM) is a supervised learning type method. Support Vector Machine (SVM) is an algorithm used for the prediction process, both in classification cases. Before the SVM model creation process is carried out, an attribute selection process will be carried out using forward selection techniques to see what attributes influence the formation of wine quality. After that, a model was created using the Support Vector Machine method using the RBF kernel function to produce classification results. There are two processes for creating a machine learning model, namely the first model is an SVM model without parameter optimization and the second model is an SVM model with parameter optimization, and the process of creating both models both use the SVM kernel function, namely the RBF kernel function. In the SVM model without carrying out parameter optimization, we obtained an optimum level of accuracy of 0.78 or 78%, while for the results of the second model, namely the SVM model with parameter optimization, we obtained an optimum level of accuracy of 0.85 or 85% with parameters C = 100 and gamma value = 0.5.

Full Text:

PDF

References


D. K. Jana, P. Bhunia, S. Das Adhikary, and A. Mishra, “Analyzing of salient features and classification of wine type based on quality through various neural network and support vector machine classifiers,” Results in Control and Optimization, vol. 11, p. 100219, Jun. 2023, doi: 10.1016/j.rico.2023.100219.

N. L. Costa, L. A. G. Llobodanin, I. A. Castro, and R. Barbosa, “Using Support Vector Machines and neural networks to classify Merlot wines from South America,” Information Processing in Agriculture, vol. 6, no. 2, pp. 265–278, Jun. 2019, doi: 10.1016/j.inpa.2018.10.003.

S. Aich, A. A. Al-Absi, K. Lee Hui, and M. Sain, “Prediction of Quality for Different Type of Wine based on Different Feature Sets Using Supervised Machine Learning Techniques,” in 2019 21st International Conference on Advanced Communication Technology (ICACT), IEEE, Feb. 2019, pp. 1122–1127. doi: 10.23919/ICACT.2019.8702017.

F. Liu and Y. He, “Use of visible and near infrared spectroscopy and least squares-support vector machine to determine soluble solids content and pH of cola beverage.,” J Agric Food Chem, vol. 55, no. 22, pp. 8883–8, Oct. 2007, doi: 10.1021/jf072057b.

H. Yu, H. Lin, H. Xu, Y. Ying, B. Li, and X. Pan, “Prediction of enological parameters and discrimination of rice wine age using least-squares support vector machines and near infrared spectroscopy.,” J Agric Food Chem, vol. 56, no. 2, pp. 307–13, Jan. 2008, doi: 10.1021/jf0725575.

S. Aich, A. A. Al-Absi, K. L. Hui, J. T. Lee, and M. Sain, “A classification approach with different feature sets to predict the quality of different types of wine using machine learning techniques,” in 2018 20th International Conference on Advanced Communication Technology (ICACT), IEEE, Feb. 2018, pp. 139–143. doi: 10.23919/ICACT.2018.8323674.

B. Chen, C. Tawiah, J. Palmer, and R. Erol, “Multi-class wine grades predictions with hierarchical support vector machines,” in 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), IEEE, Jul. 2017, pp. 111–115. doi: 10.1109/FSKD.2017.8392918.

S. Dey, S. Wasif, D. S. Tonmoy, S. Sultana, J. Sarkar, and M. Dey, “A Comparative Study of Support Vector Machine and Naive Bayes Classifier for Sentiment Analysis on Amazon Product Reviews,” in 2020 International Conference on Contemporary Computing and Applications (IC3A), IEEE, Feb. 2020, pp. 217–220. doi: 10.1109/IC3A48958.2020.233300.

S. Chhikara, P. Bansal, and K. Malik, “Wine Quality Prediction Using Machine Learning Techniques,” in Lecture Notes in Networks and Systems, vol. 645 LNNS, Springer Science and Business Media Deutschland GmbH, 2023, pp. 137–148. doi: 10.1007/978-981-99-0769-4_14.

F. J. Acevedo, J. Jiménez, S. Maldonado, E. Domínguez, and A. Narváez, “Classification of Wines Produced in Specific Regions by UV−Visible Spectroscopy Combined with Support Vector Machines,” J Agric Food Chem, vol. 55, no. 17, pp. 6842–6849, Aug. 2007, doi: 10.1021/jf070634q.

Basvaraj. S. Anami, K. Mainalli, S. Kallur, and V. Patil, “A Machine Learning Based Approach for Wine Quality Prediction,” in 2022 2nd Asian Conference on Innovation in Technology (ASIANCON), IEEE, Aug. 2022, pp. 1–6. doi: 10.1109/ASIANCON55314.2022.9908870.

S. Kumar, K. Agrawal, and N. Mandan, “Red Wine Quality Prediction Using Machine Learning Techniques,” in 2020 International Conference on Computer Communication and Informatics (ICCCI), IEEE, Jan. 2020, pp. 1–6. doi: 10.1109/ICCCI48352.2020.9104095.

K. R. Dahal, J. N. Dahal, H. Banjade, and S. Gaire, “Prediction of Wine Quality Using Machine Learning Algorithms,” Open J Stat, vol. 11, no. 02, pp. 278–289, 2021, doi: 10.4236/ojs.2021.112015.


Refbacks

  • There are currently no refbacks.


Flag Counter

 International Journal of Engineering Computing Advanced Research (IJECAR) (e-ISSN : xxxx-xxxx, p-ISSN : xxxx-xxxx) is published by ARCES.

 

This journal is under licensed of Creative Commons Attribution 4.0 International License.

Visitor Stats