The Role of Artificial Intelligence in Productivity: A Case Study of Wine Quality Prediction

Abstract

Artificial intelligence has been used in many areas in recent years and has achieved quite successful results. Like using artificial intelligence from healthcare to driverless vehicles, it also has often been used to increase productivity in the production sector. In this study, we tried to draw a framework for the use of artificial intelligence algorithms in a data set that is not normally distributed. Any artificial intelligence algorithm can be easily applied on normally distributed data sets, while data sets that do not normally distributed require a different operation to the data itself or it is necessary to revise the theoretical structure of the algorithm. In this regard, three different methodologies are applied in this study. Initially, Support Vector Machines, which are often used in the literature, is used. In addition, Weighted Support Vector Machines, which is the revised version of the Support Vector Machines to produce successful results in abnormal distributed data sets. Finally, the Synthetic Minority Oversampling Technique (SMOTE) is applied and the data set used was artificially converted to normal distribution. Three techniques are compared in terms of sensitivity, specificity, precision, prevalence, F-1 score, and G-Mean evaluation criteria were compared. According to the results of the study, Weighted Support Vector Machines produced the most successful results according to the evaluation criteria used.

Keywords

• Support Vector Machines
• Weighted Support Vector Machines
• SMOTE

Verimlilikte Yapay Zeka’nın Rolü: Şarap Kalitesinin Tahminine Yönelik Bir Vaka Çalışması

Öz

Yapay zeka son yıllarda birçok alanda kullanılmaya başlanmış ve oldukça başarılı sonuçlar elde edilmiştir. Sağlık sektöründen sürücüsüz araçlara kadar birçok alanda kullanılan yapay zeka, üretim sektöründe de verimliliğin artırılması için sıklıkla kullanılmıştır. Bu çalışmada normal olarak dağılmamış bir veri setinde yapay zeka algoritmalarının kullanılmasına yönelik bir çerçeve çizilmeye çalışılmıştır. Normal dağılım gösteren veri setlerinde herhangi bir yapay zeka algoritması kolaylıkla uygulanabilirken normal dağılım göstermeyen veri setlerinde ya verinin kendisine farklı bir işlem uygulanması gerekir veya algoritmanın teorik yapısının revize edilmesi gerekmektedir. Bu açıdan bu çalışmada iki farklı yöntemde uygulanmıştır. İlk olarak literatürde sıklıkla kullanılan Destek Vektör Makinaları kullanılmıştır. Buna ek olarak Destek Vektör Makinalarının normal dağılmayan veri setlerinde başarılı sonuçlar vermesi için uyarlanmış şekli olan Ağırlıklandırılmış Destek Vektör Makineleri uygulanmıştır. Son olarak Sentetik Azınlık Aşırı Örnekleme Tekniği (SMOTE) tekniği uygulanmış ve kullanılan veri seti yapay olarak normal dağılıma yakınsanmıştır. Kullanılan üç teknikte duyarlılık, hassaslık, özgüllük, yaygınlık, F skor ve Geometrik Ortalama (G-Mean) değerlendirme kriterleri açısından karşılaştırılmıştır. Çalışma sonucuna göre Ağırlıklandırılmış Destek Vektör Makineleri kullanılan değerlendirMe kriterlerine göre en başarılı sonuçları vermiştir.

Anahtar Kelimeler

• Destek Vektör Makineleri
• Ağırlıklandırılmış Destek Vektör Makineleri
• SMOTE

Kaynakça

1. Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 144–152.
2. Chalfin, A., Danieli, O., Hillis, A., Jelveh, Z., Luca, M., Ludwig, J., & Mullainathan, S. (2016). Productivity and selection of human capital with machine learning. American Economic Review, 106(5), 124–127.
3. Chawla, N. V, Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.
4. Chen, Q., Xu, J., & Koltun, V. (2017). Fast image processing with fully-convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, 2497–2506.
5. Cortez, P., Cerdeira, A., Almeida, F., Matos, T., & Reis, J. (2009). Modeling wine preferences by data mining from physicochemical properties. Decision Support Systems, 47(4), 547–553.
6. Fang, R. (2006). Induction machine rotor diagnosis using support vector machines and rough set. International Conference on Intelligent Computing, 631–636.
7. Jack, L. B., & Nandi, A. K. (2002). Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mechanical Systems and Signal Processing, 16(2–3), 373–390.
8. Liakos, K., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), 2674.

9. Manyika, J. (2017). A FUTURE THAT WORKS: AI, AUTOMATION, EMPLOYMENT, AND PRODUCTIVITY.
10. Mondal, A., Ghosh, A., & Ghosh, S. (2018). Scaled and oriented object tracking using ensemble of multilayer perceptrons. Applied Soft Computing, 73, 1081–1094.
11. Poyhonen, S., Negrea, M., Arkkio, A., Hyotyniemi, H., & Koivo, H. (2002). Fault diagnostics of an electrical machine with multiple support vector classifiers. Intelligent Control, 2002. Proceedings of the 2002 IEEE International Symposium On, 373–378.
12. Segatori, A., Marcelloni, F., & Pedrycz, W. (2018). On distributed fuzzy decision trees for big data. IEEE Transactions on Fuzzy Systems, 26(1), 174–192.
13. Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I.,
14. Panneershelvam, V., & Lanctot, M. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484.
15. Sugumaran, V., Muralidharan, V., & Ramachandran, K. I. (2007). Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing. Mechanical Systems and Signal Processing, 21(2), 930–942.
16. Ünlü, R., & Xanthopoulos, P. (2017). A weighted framework for unsupervised ensemble learning based on internal quality measures. Annals of Operations Research, 1–19.
17. Ünlü, R., & Xanthopoulos, P. (2019). Estimating the number of clusters in a dataset via consensus clustering. Expert Systems with Applications.
18. Veropoulos, K., Campbell, C., & Cristianini, N. (1999). Controlling the sensitivity of support vector machines. Proceedings of the International Joint Conference on AI, 55, 60.
19. Xanthopoulos, P., & Razzaghi, T. (2014). A weighted support vector machine method for control chart pattern recognition. Computers & Industrial Engineering, 70, 134–149.
20. Zhitong, C., Jiazhong, F., Hongpingn, C., Guoguang, H., & Ritchie, E. (2003). Support vector machine used to diagnose the fault of rotor broken bars of induction motors. Electrical Machines and Systems, 2003. ICEMS 2003. Sixth International Conference On, 2, 891–894.