Using Machine Learning Algorithms to Detect Milk Quality

Abstract

Machine learning algorithms are used successfully in many sectors. The data formed by the development of digital technology are analyzed with machine learning algorithms and estimation, classification or clustering processes are carried out. Today, the food industry has a very important place and it will be very useful to follow the quality of the products produced and to determine in a short time. Milk is a product that people benefit from raw or processed. Milk is also a perishable product. Each gram milk with poor quality or structure can cause tons of milk to deteriorate, thus causing great financial losses. Millions of bacteria can form in spoiled milk in a very short time. In this way, if people consume milk or dairy products, situations that endanger human health may occur. In this study; A study was conducted in which milk quality was determined by machine learning algorithms. Seven features were used to determine milk quality. In the study, the Milk Quality dataset obtained from the open source Kaggle data repository was used. There are 1059 sample data in the data set. By using 7 attributes of milk samples, low, medium and high quality classification of milk was carried out. In the classification estimation phase, commonly used Neural Network (Neural Network: NN) and Adaptive Boosting (AdaBoost: AB) algorithms were used. Orange platform, which is open source and written in python, was used as the application platform. Orange is a platform with a widely used and see user interface. In the application phase, the results obtained with each algorithm were presented with visual graphics and comparisons were made. In the test phase, 100 milk data samples were used separately for each class in order to achieve a balanced learning. Random samples were selected from the data set for training. According to the results obtained; Classification accuracy (CA) success was achieved by 99.9% with AdaBoost algorithm and 95.4% with Neural Network algorithm. More successful results were obtained with the AdaBoost algorithm than the Neural network algorithm.

Keywords

• Machine learning
• Neural network
• Adaboost
• Smart decision system
• Quality control
• Food safety

References

1. Albanese D., Visintainer R., Merler S., Riccadonna S., Jurman G., Furlanello C. 2012. mlpy: Machine Learning Python. arXiv:1202-6548v2
2. Balaban M. E., Kartal E. 2018. Veri madenciliği ve makine öğrenmesi temel algoritmaları ve R Dili ile Uygulamalar, 2. Basım, Çağlayan Kitap & Yayıncılık & Eğitim, İstanbul, Türkiye, pp. 48-72.
3. Chung J. R., Kwon J., Choe Y. 2009. Evolution of recollection and prediction in neural networks, International Joint Conference on Neural Networks. Atlanta,14-19 June 2009, pp. 571-577.
4. Çelik A. 2022. Improving Iris Dataset Classification Prediction Achievement by Using Optimum k Value of kNN Algorithm, Eskişehir Türk Dünyası Uygulama ve Araştırma Merkezi Bilişim Dergisi, 3(2): 23-30.
5. Demsar J., Curk T., Erjavec A., Gorup C., Hocevar T., Milutinovic M., Mozina M., Polajnar M., Toplak M., Staric A., Stajdohar M., Umek L., Zagar L., Zbontar J., Zitnik M., Zupan B. 2013. Orange: Data Mining Toolbox in Python, Journal of Machine Learning Research, 14: 2349−2353.
6. Kaggle Inc. 2022. Kaggle. https://www.kaggle.com/general (accessed 10 July 2022).
7. Kanawaday A., Sane A. 2017. Machine learning for predictive maintenance of industrial machines using IoT sensor data, 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, 24-26 November 2017, pp. 87-90.
8. Keshavamurthy, Mariyam S. J., Meghamala M., Meghashree M., Neha, 2019. Automatized Food Quality Detection and Processing System Using Neural Networks. 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT), Bangalore, 17-18 May 2019, pp. 1442-1446.

9. Kumar M., Gupta S., Gao X.Z., Singh A. 2019. Plant Species Recognition Using Morphological Features and Adaptive Boosting Methodology, in IEEE Access. 7, 163912-163918. Küçük R., Tapkı N. 2020. Hatay İlinde Süt ve Süt Ürünleri Üreten İşletmelerin Üretim ve Pazarlama Yapısı, Hayvan Bilimi ve Ürünleri Dergisi, 3 (2) : 104-119.
10. University of Ljubljana. 2022. Orange Data Mining. https://orangedatamining.com/, (accessed 12 Aug 2022).
11. Ozkan I.A., Koklu M., Saraçoğlu R. 2021. Classification of Pistachio Species Using Improved K-NN Classifier, Progress in Nutrition, 23(2):1-9.
12. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion, B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay E., Louppe G. 2012. Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research, 12: 2825-2830.
13. Ricci M., Vasquez J. A. T., Turvani G., Sirena I., Casu M. R., Vipiana F. 2021. Microwave Sensing for Food Safety: a Neural Network Implementation. In IEEE Conference on Antenna Measurements & Applications(CAMA), Antibes Juan-les-Pins, 15-17 November 2021, pp. 444-447.
14. Sambasivam, G., Amudhavel J., Sathya, G. 2020. A Predictive Performance Analysis of Vitamin D Deficiency Severity Using Machine Learning Methods, In IEEE Access. 8: 109492-109507.
15. Singh P., Kaur S., Sharma S., Sharma G., Vashisht S., Kumar V. 2021. Malware Detection Using Machine Learning, 2021 International Conference on Technological Advancements and Innovations (ICTAI), Tashkent, 10-12 November 2021, pp. 11-14.
16. Sun Y., Kamel M.S., Wang Y. 2006. Boosting for Learning Multiple Classes with Imbalanced Class Distribution. 6th International Conference on Data Mining (ICDM'06), Hong Kong, 18-22 Dec 2006, pp. 592-602.
17. Tahtacı B., Canbay B. 2020. Android Malware Detection Using Machine Learning, Innovations in Intelligent Systems and Applications Conference (ASYU), Istanbul, 15-17 October 2020, pp. 1-6.
18. Thange U., Shukla V.K., Punhani R., Grobbelaar W. 2021. Analyzing COVID-19 Dataset through Data Mining Tool “Orange”, 2nd International Conference on Computation, Automation and Knowledge Management (ICCAKM), Dubai, 9-21 January 2021, pp. 198-203.
19. Titova T., Nachev V., Damyanov C. 2018. Collective Neural Classifiers for Food Quality Applications. ANNA '18; Advances in Neural Networks and Applications. Bulgaria, 15-17 September 2018, pp. 1-5.
20. Uçan N. O., Onur O., Albora M. 2006. Görüntü İşleme Teknikleri ve Mühendislik Uygulamaları, 1. Baskı, Nobel Yayın Dağıtım.
21. Wang F., Li F., He F., Wang R., Yu W., Nie F. 2019. Feature Learning View Point of Adaboost and a New Algorithm, In IEEE Access, 7: 149890-149899.
22. Xiao L., Xia K., Tian H. 2019. Research on Classification Model of Fermented Milk Quality Control Based on Data Mining. International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), Shanghai, 21-24 November 2019, pp. 324-327.
23. Vaishnav D., Rao B.R. 2018. Comparison of Machine Learning Algorithms and Fruit Classification using Orange Data Mining Tool, 3rd International Conference on Inventive Computation Technologies (ICICT). Coimbatore, 15-16 November 2018, pp. 603-607.
24. Vrindavanam J., Srinath R., Shankar H.H, Nagesh G. 2021. Machine Learning based COVID-19 Cough Classification Models - A Comparative Analysis, 5th International Conference on Computing Methodologies and Communication (ICCMC), Erode, 08-10 April 2021, pp. 420-426.