Ensuring Market Authenticity of Labaneh: Machine Learning-Driven Analysis of Fatty Acid Profiles for Detecting Non-Milk Fat Adulterants in Jordanian Products

  • Vaishali V. Raje, S. A. Surale-Patil, Dheeraj Mane
Keywords: Labaneh, Fatty acid profiles, Non-milk fat adulterants, Machine learning, Jordan


Labaneh, a traditional Middle Eastern dairy product, has gained popularity not only domestically but also internationally. However, concerns regarding the authenticity of Labaneh due to potential adulteration with non-milk fats have emerged. Such adulteration not only compromises the quality and nutritional value of Labaneh but also poses health risks to consumers. Therefore, there is an urgent need for reliable and efficient methods to detect non-milk fat adulterants in Labaneh products. In this study, we propose a novel approach utilizing machine learning-driven analysis of fatty acid profiles to detect non-milk fat adulterants in Labaneh. Fatty acid profiles serve as unique chemical fingerprints that can provide valuable information about the composition of dairy products. By employing machine learning algorithms, such as support vector machines (SVM) and artificial neural networks (ANN), we aim to develop predictive models capable of accurately identifying adulterated Labaneh samples. The study focuses on Labaneh products from Jordan, a region renowned for its rich culinary heritage. Samples of authentic Labaneh and potentially adulterated Labaneh containing various concentrations of non-milk fats are collected from local markets across Jordan. Fatty acid methyl esters (FAMEs) are extracted from the samples and analyzed using gas chromatography-mass spectrometry (GC-MS) to obtain their fatty acid profiles.


[1] Yu, D.; Gu, Y. A machine learning method for the fine-grained classification of green tea with geographical indication using a mos-based electronic nose. Foods 2021, 10, 795.
[2] Tachie, C.; Aryee, A.N.A. Using machine learning models to predict quality of plant-based foods. Curr. Res. Food Sci. 2023, 7, 100544.
[3] Othman, S.; Mavani, N.R.; Hussain, M.A.; Abd Rahman, N.; Mohd Ali, J. Artificial intelligence-based techniques for adulteration and defect detections in food and agricultural industry: A review. J. Agric. Food Res. 2023, 12, 100590.
[4] Yakar, Y.; Karadağ, K. Identifying olive oil fraud and adulteration using machine learning algorithms. Quim. Nova 2022, 45, 1245–1250.
[5] Lim, K.; Pan, K.; Yu, Z.; Xiao, R.H. Pattern recognition based on machine learning identifies oil adulteration and edible oil mixtures. Nat. Commun. 2020, 11, 5353.
[6] Honggen, Z.; Zhenyu, W.; Oscar, L. Development and validation of a GC–FID method for quantitative analysis of oleic acid and related fatty acids. J. Pharm. Anal. 2015, 5, 223–230.
[7] Grazina, L.; Rodrigues, P.J.; Igrejas, G.; Nunes, M.A.; Mafra, I.; Arlorio, M.; Oliveira, M.B.P.P.; Amaral, J.S. Machine Learning Approaches Applied to GC-FID Fatty Acid Profiles to Discriminate Wild from Farmed Salmon. Foods 2020, 9, 1622.
[8] Mahrous, E.; Chen, R.; Zhao, C.; Farag, M.A. Lipidomics in food quality and authentication: A comprehensive review of novel trends and applications using chromatographic and spectroscopic techniques. Crit. Rev. Food Sci. 2023, 1–24.
[9] Covaciu, F.D.; Feher, I.; Molnar, C.; Floare-Avram, V.; Dehelean, A. Characterization of the Fatty Acid and Elemental Composition of Human Milk with Chemometric Processing to Determine the Nutritional Value. Anal. Lett. 2023, 56, 344–356.
[10] Ferreira, J.E.V.; Miranda, R.M.; Figueiredo, A.F.; Barbosa, J.P.; Brasil, E.M. Box-and-Whisker Plots Applied to Food Chemistry. J. Chem. Educ. 2016, 93, 2026–2032.
[11] Berghian-Grosan, C.; Magdas, D.A. Raman spectroscopy and machine-learning for edible oils evaluation. Talanta 2020, 218, 121176.
[12] Berghian-Grosan, C.; Magdas, D.A. Application of Raman spectroscopy and Machine Learning algorithms for fruit distillates discrimination. Sci. Rep. 2020, 10, 21152.
[13] Magdas, D.A.; Guyon, F.; Berghian-Grosan, C.; Muller Molnar, C. Challenges and a step forward in honey classification based on Raman spectroscopy. Food Control 2021, 123, 107769.
[14] Magdas, D.A.; David, M.; Berghian-Grosan, C. Fruit spirits fingerprint pointed out through artificial intelligence and FT-Raman spectroscopy. Food Control 2022, 133, 108630
[15] Rutkowska, J.; Adamska, A.; Sinkiewicz, I.; Bialek, M. Composition of fatty acids in selected sorts of biscuits, offered for children. Acta Aliment. 2012, 41, 433–442.
[16] Negoita, M.; Mihai, A.L.; Iorga, E.; Belc, N. Fatty Acids and Trans Fatty Acids Profile of Potato Chips and French Fries Marketed in Romania. Rev. Chim. 2020, 71, 458–467.
[17] Zhang, Y.; Zhang, T.; Fan, D.; Li, J.; Fan, L. The description of oil absorption behaviour of potato chips during the frying. LWT-Food Sci. Technol. 2018, 96, 119–126.
[18] Stroher, G.L.; Rodrigues, A.C.; Gohara, A.K.; Visentainer, J.V.; Matsushita, M.; Evelazio de Souza, N. Fatty acid quantification in different types of cookies with emphasis on trans Fatty Acids. Acta Sci. Technol. 2012, 34, 105–110.
How to Cite
Vaishali V. Raje. (2024). Ensuring Market Authenticity of Labaneh: Machine Learning-Driven Analysis of Fatty Acid Profiles for Detecting Non-Milk Fat Adulterants in Jordanian Products. Revista Electronica De Veterinaria, 25(1), 502 - 512. Retrieved from https://www.veterinaria.org/index.php/REDVET/article/view/539