Spektroskopik Veri ve Makine Öğrenimi Kullanarak Sütteki Nişasta Sahteciliğinin Sınıflandırılması

Year 2024, Volume: 16 Issue: 1, 221 - 226, 31.01.2024

Yeliz Durgun

https://doi.org/10.29137/umagd.1379171

Abstract

Bu kapsamlı araştırmada, Çok Katmanlı Algılayıcı, IBk, KStar, M5Rules ve RandomForest gibi çeşitli makine öğrenimi algoritmaları, spektroskopik veri kullanarak süt ürünlerindeki sahteciliği tespit etme etkinlikleri açısından derinlemesine değerlendirilmiştir. Algoritmalar, ham ve sahte süt örnekleri üzerinde yapılan kontrollü deneyler aracılığıyla titizlikle uygulanmış ve değerlendirilmiştir. Özellikle, IBk ve KStar algoritmaları, sahteciliği tespit etmede yüzde 100'lik mükemmel bir doğruluk oranı ile öne çıkmıştır, bu da bu alandaki üstün yeteneklerini vurgulamaktadır. Ek olarak, Karar Tablosu algoritması da son derece iyi bir performans göstererek, 0.9871'lik dikkate değer bir korelasyon katsayısı elde etmiştir. Bu umut verici sonuçlar, makine öğrenimi algoritmalarının sütteki sahteciliği tespit etme konusunda güvenilir ve kesin araçlar olarak inkar edilemez potansiyellerini vurgulamaktadır. Bu tür teknolojik müdahaleler, piyasada bulunan süt ve süt ürünlerinin güvenlik ve kalite standartlarını yükseltmede kritik bir rol oynamaktadır. Ayrıca, bu gelişmiş makine öğrenimi tekniklerinin uygulanması, tüketicilere değerli bir koruma katmanı sağlamakta, süt endüstrisinde yaygın sahtecilik uygulamalarıyla mücadelede önemli bir rol oynamakta ve katı gıda güvenliği standartlarına uyumu sağlamaktadır. Bu yöntemler, endüstri oyuncuları ve düzenleyici kurumlar için vazgeçilmez olabilir, kamusal sağlığın korunmasına önemli ölçüde katkı sağlayabilir.

Keywords

Spektroskopi, Makine Öğrenimi Algoritmaları, Süt Sahteciliği, Gıda Güvenliği

Classification of Starch Adulteration in Milk Using Spectroscopic Data and Machine Learning

Abstract

In this comprehensive research, an in-depth evaluation of several machine learning algorithms, including Multilayer Perceptron, IBk, KStar, M5Rules, and RandomForest, is conducted to ascertain their effectiveness in detecting adulteration in milk products using spectroscopic data. The algorithms were rigorously deployed and assessed through a series of controlled experiments involving both raw and adulterated milk samples. Notably, IBk and KStar algorithms emerged with a perfect accuracy rate of 100% in identifying adulteration, highlighting their superior capability in this domain. Additionally, the Decision Table algorithm also performed exceptionally well, achieving a remarkable correlation coefficient of 0.9871. These promising results emphasize the undeniable potential of machine learning algorithms as reliable and precise tools for detecting adulteration in milk. Such technological interventions play a critical role in elevating the safety and quality standards of milk and milk-based products in the market. Moreover, the deployment of these advanced machine-learning techniques provides an invaluable layer of consumer protection, plays a significant role in combating widespread fraudulent practices in the milk industry, and ensures compliance with stringent food safety standards. These methodologies could be indispensable for both industry players and regulatory bodies, significantly contributing to the safeguarding of public health.

Keywords

Spectroscopy, Classification Models, Machine Learning Algorithms, Milk Adulteration, Food Safety

References

• Banks, W, C T Greenwood, & D D Muir. (1971) “The Characterization of Starch and Its Components. Part 3. The Technique of Semi-Micro, Differential, Potentiometric, Iodine Titration, and the Factors Affecting It.” Starch-St{ä}rke 23 (4): 118–124.
• Banti, Misgana. (2020a). “Food adulteration and some methods of detection, review.”International Journal of Nutrition and Food Sciences 9 (3): 86–94.
• Bojarczuk, Adrianna, Sylwia Sk, Amin Mousavi Khaneghah, & Krystian Marsza. (2022). “Health benefits of resistant starch: A review of the literature.” Journal of functional foods 93:105094.
• Borin, Alessandra, Marco Flores Ferrao, Cesar Mello, Danilo Althmann Maretto, & Ronei Jesus Poppi. (2006). “Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk.” Analytica chimica acta 579 (1): 25–32.
• Chauhan, Sneh Lata, Kruti Debnath Mandal Priyanka, Babul Rudra Paul, & Chinmoy Maji. (2019). “Adulteration of milk: A Review.” International Journal of Chemical Studies 7 (1): 2055–2057.
• Dugyala, Venkateshwar Rao, Shantanu Pradhan, & Madivala G Basavaraj. (2023a). “Sessile drop evaporation approach to detect starch adulteration in milk.” Food Control 143:109272.
• Harindran, Aswini, Sabin Hashmi, & V Madhurima. (2022). “Pattern formation of dried droplets of milk during different processes and classifying them using artificial neural networks.” Journal of Dispersion Science and Technology 43 (12): 1838–1847.
• Jha, Shyam Narayan, Pranita Jaiswal, Manpreet Kaur Grewal, Mansha Gupta, & Rishi Bhardwaj. (2016). “Detection of adulterants and contaminants in liquid foods—a review.” Critical reviews in food science and nutrition 56 (10): 1662–1684.
• Kumar, Virkeshwar, & Susmita Dash. (2021). “Evaporation-based low-cost method for the detection of adulterant in milk.” ACS omega 6 (41): 27200–27207.
• Manning, Louise & Jan Mei Soon. (2016). “Food safety, food fraud, and food defense: a fast evolving literature.” Journal of food science 81 (4): 823–834.
• Nacul, Hasibi Zavala, & Cesar Revoredo-Giha. (2022). “Food safety and the informal milk supply chain in Kenya.” Agriculture & Food Security 11 (1): 8.
• Nascimento, Carina F, Poliana M Santos, Edenir Rodrigues Pereira-Filho, & Fábio RP Rocha. (2017). “Recent advances on determination of milk adulterants.” Food chemistry 221:1232–1244.
• Pointing, John, Yunes Ramadan Al-Teinaz, John Lever, Mary Critchley, & Stuart Spear.(2020). “Food fraud.” The Halal Food Handbook, pp. 321–329.
• Reddy, D Maheswara, K Venkatesh, & C Venkata Sesha Reddy. (2017). “Adulteration of milk and its detection: a review.” International Journal of Chemical Studies 5 (4): 613–617.
• Sadek, Celine, Pierre Schuck, Yannick Fallourd, Nicolas Pradeau, Cecile Le Floch-Fouere, & Romain Jeantet. (2015). “Drying of a single droplet to investigate process-structure-function relationships: a review.” Dairy Science and Samp; Technology 95 (6): 771–794.
• Sammut, Jesmond, Karthik Gopi, Neil Saintilan, & Debashish Mazumder. (2021).Facing the challenges of food fraud in the global food system.
• Singh, Parminder, & Neeraj Gandhi. (2015). “Milk preservatives and adulterants: processing, regulatory and safety issues.” Food Reviews International 31 (3): 236–261.
• Spink, John, Brian Bedard, John Keogh, Douglas C Moyer, Joe Scimeca, & Akhila Vasan. (2019). “International survey of food fraud and related terminology: Preliminary results and discussion.” Journal of food science 84 (10): 2705–2718.
• Spink, John, Neal D Fortin, Douglas C Moyer, Hong Miao, & Yongning Wu. (2016). “Food fraud prevention: policy, strategy, and decision-making-implementation steps for a Government Agency or industry.” Chimia 70 (5): 320–320.
• Spink, John, &Douglas C Moyer. (2011a). “Defining the public health threat of food fraud.” Journal of food science 76 (9): 157–163.
• Spink, John, & Douglas C Moyer. (2011b). “Defining the public health threat of food fraud.” Journal of food science 76 (9): 157–163.
• Thangaraju, Suka, Nikitha Modupalli, & Venkatachalapathy Natarajan. (2021). “Food adulteration and its impacts on our health/balanced nutrition.” Food Chemistry: The Role of Additives, Preservatives and Adulteration, pp. 189–216.
• Visciano, Pierina, & Maria Schirone. (2021). “Food frauds: Global incidents and misleading situations.” Trends in Food Science & Technology 114:424–442.
• Weinstein, Louis, Robert E Olson, Theodore B Van Itallie, Elizabeth Caso, Doris Johnson, & Franz J Ingelfinger. (1961). “Diet as related to gastrointestinal function.” JAMA 176 (11): 935–941