A Method for Rapid Evaluation of Milk Quality Parameters Using Optical Spectroscopy and Intelligent Data Analysis Algorithms

Introduction: Spectroscopic methods are widely used to monitor the quality parameters of milk. However, their application in rapid analysis is limited by the size of the equipment and the complexity of spectral data processing. At the same time, methods that ensure the compactness of the measurement system while enabling the extraction of informative features from multidimensional spectral data remain insufficiently developed.

Purpose: Development of an optical express method based on multispectral registration of backscattered radiation followed by intelligent data analysis.

Materials and Methods: The method is based on a combination of scattering spectrophotometry and intelligent data analysis. To record the spectral characteristics, a compact optical system was developed based on a multichannel spectrum analyzer, measuring the intensity of backscattered radiation at 18 fixed wavelengths in the 410–940 nm range. The obtained spectral data were processed using visual analysis and principal component analysis to identify differences between samples in three–dimensional space. The study included samples of cow’s milk with different fat mass fractions, including samples diluted with distilled water and samples aged until natural souring occurred.

Results: Principal component analysis revealed differentiation of the samples according to fat mass fraction and physicochemical state. Group separation was observed in the space of the first three principal components, with a total explained variance exceeding 90%. The obtained results demonstrated good reproducibility for measurements of samples with identical characteristics. The greatest contribution to the separation was made by signals at wavelengths of 460, 510, and 940 nm (first principal component); 560, 585, and 645 nm (second principal component); and 680, 730, and 810 nm (third principal component), indicating their informativeness for detecting changes.

Conclusion: The proposed method makes it possible to detect changes associated with fat concentration and physicochemical state and ensures the reproducibility of the obtained results using the developed compact optical system. In the future, it can be applied for rapid assessment of milk quality at any stage of production. Furthermore, the method has the potential to be integrated into automated monitoring systems.

1. Barkovskaya I.A., Turovskaya S.N., Illarionova E.E., Yaryshev V.Yu., Bliadze V.G., Kondratenko V.V. Comparison of IR and Raman spectroscopy methods for assessing structural changes in milk during heat treatment. FOOD METAENGINEERING. 2025;3(3):21–38. (In Russ.) https://doi.org/10.37442/fme.2025.3.91

2. Khan A.V., Lazareva E.G., Fomenko O.Yu. Optimization of Molecular Genetic Method for Identification of Dairy Raw Materials. FOOD METAENGINEERING. 2023;1(4):39–47. (In Russ.) https://doi.org/10.37442/fme.2023.4.29

3. Khovatov, N. E., Khovatov, A. E., & Perkov, A. A. (2021). Assessment of Milk Quality. Modern Science, (5–2), 180–185. (In Russ.)

4. Aernouts, B., Polshin, E., Lammertyn, J., & Saeys, W. (2011, May). Rapid analysis of raw milk for cow health monitoring. In NIR 2011, Date: 2011/05/13–2011/05/20, Location: Cape Town, South Africa. https://doi.org/10.3390/ASEC2023–16302

5. Aernouts, B., Van Beers, R., Watté, R., Huybrechts, T., Lammertyn, J., & Saeys, W. (2015). Visible and near–infrared bulk optical properties of raw milk. Journal of dairy science, 98(10), 6727–6738. https://doi.org/10.3168/jds.2015–9630

6. Aska, S. A., Nurillah, A. S., Benani, K., & Azizah, N. W. (2023). Determination of Protein Content of Processed Dairy Products Using the Kjeldahl Method. Journal on Biology and Instruction, 3(1). https://doi.org/10.26555/joubins.v3i1.7055

7. Beć, K. B., Grabska, J., & Huck, C. W. (2022). Miniaturized NIR spectroscopy in food analysis and quality control: Promises, challenges, and perspectives. Foods, 11(10), 1465. https://doi.org/10.3390/foods11101465

8. Chauhan, S., Powar, P., & Mehra, R. (2021). A review on nutritional advantages and nutraceutical properties of cow and goat milk. Int. J. Appl. Res, 7(10), 101–105. http://dx.doi.org/10.22271/allresearch.2021.v7.i10b.9025

9. Diaz–Olivares, J. A., Gote, M. J., Saeys, W., Adriaens, I., & Aernouts, B. (2024). Near–infrared spatially–resolved spectroscopy for milk quality analysis. Computers and Electronics in Agriculture, 219, 108783. https://doi.org/10.1016/j.compag.2024.108783

10. Gastélum–Barrios, A., Soto–Zarazúa, G. M., Escamilla–García, A., Toledano–Ayala, M., Macías–Bobadilla, G., & Jauregui–Vazquez, D. (2020). Optical methods based on ultraviolet, visible, and near–infrared spectra to estimate fat and protein in raw milk: A review. Sensors, 20(12), 3356. https://doi.org/10.3390/s20123356

11. Greenacre, M., Groenen, P. J., Hastie, T., d’Enza, A. I., Markos, A., & Tuzhilina, E. (2022). Principal component analysis. Nature Reviews Methods Primers, 2(1), 100. https://doi.org/10.1038/s43586–023–00209–y

12. Hasan, B. M. S., & Abdulazeez, A. M. (2021). A review of principal component analysis algorithm for dimensionality reduction. Journal of Soft Computing and Data Mining, 2(1), 20–30.

13. Hayes, M. (2020). Measuring protein content in food: An overview of methods. Foods, 9(10), 1340. https://doi.org/10.3390/foods9101340

14. Iweka, P., Kawamura, S., Mitani, T., & Kawaguchi, T. (2023). Online near–infrared spectroscopy for the measurement of cow milk quality in an automatic milking system. Engineering Proceedings, 56(1), 145. https://doi.org/10.3390/ASEC2023–16302

15. Jhanwar, A., & Ward, R. E. (2014). Particle size distribution and lipid composition of skim milk lipid material. International Dairy Journal, 36(2), 110–117. https://doi.org/10.1016/j.idairyj.2014.01.010

16. Khan, H. H., McCarthy, U., Esmonde–White, K., Casey, I., & O'Shea, N. (2023). Potential of Raman spectroscopy for in–line measurement of raw milk composition. Food Control, 152, 109862. https://doi.org/10.1016/j.foodcont.2023.109862

17. Liu, Y., Wen, Y., Hao, X., Xu, L., Zhao, X., & Ping, J. (2025). Recent advances in analytical technologies and devices for raw milk quality. TrAC Trends in Analytical Chemistry, 118510. https://doi.org/10.1016/j.trac.2025.118510

18. Loudiyi, M., Temiz, H. T., Sahar, A., Haseeb Ahmad, M., Boukria, O., Hassoun, A., & Aït–Kaddour, A. (2022). Spectroscopic techniques for monitoring changes in the quality of milk and other dairy products during processing and storage. Critical Reviews in Food Science and Nutrition, 62(11), 3063–3087. https://doi.org/10.1080/10408398.2020.1862754

19. Meena, S., Debnath, P. P., Ranvir, S. G., & Rai, D. C. (2023). Physicochemical characteristics of milk. In The Chemistry of Milk and Milk Products (pp. 109–131). Apple Academic Press.

20. Mhapsekar, R., Kilbane, D., Davy, S., Abraham, L., Fenelon, M., & O'Shea, N. (2025). A systematic review of the internet of things and artificial intelligence applications in milk quality monitoring and analysis. International Journal of Dairy Technology, 78(3), e70049. https://doi.org/10.1111/1471–0307.70049

21. Motshakeri, M., Sharma, M., Phillips, A. R., & Kilmartin, P. A. (2022). Electrochemical methods for the analysis of milk. Journal of Agricultural and Food Chemistry, 70(8), 2427–2449. https://doi.org/10.1021/acs.jafc.1c06350

22. Olson, D. W., White, C. H., & Richter, R. L. (2004). Effect of pressure and fat content on particle sizes in microfluidized milk. Journal of Dairy Science, 87(10), 3217–3223. https://doi.org/10.1016/j.idairyj.2014.01.010

23. Perez–Gonzalez, C., Garcia–Hernandez, C., Garcia–Cabezon, C., Rodriguez–Mendez, M. L., Dias, L., & Martin–Pedrosa, F. (2024). Analysis of milk adulteration by means of a potentiometric electronic tongue. Journal of Dairy Science, 107(11), 9135–9144. https://doi.org/10.3168/jds.2024–25140

24. Pu, Y., Pérez–Marín, D., O’Shea, N., & Garrido–Varo, A. (2021). Recent advances in portable and handheld NIR spectrometers and applications in milk, cheese and dairy powders. Foods, 10(10), 2377. https://doi.org/10.3390/foods10102377

25. Riu, J., Gorla, G., Chakif, D., Boqué, R., & Giussani, B. (2020). Rapid analysis of milk using low–cost pocket–size NIR spectrometers and multivariate analysis. Foods, 9(8), 1090. https://doi.org/10.3390/foods9081090

26. Shao, Y., Yuan, Y., Xi, Y., Zhao, T., & Ai, N. (2023). Effects of homogenization on organoleptic quality and stability of pasteurized milk samples. Agriculture, 13(1), 205. https://doi.org/10.3390/agriculture13010205

27. Cheng, S., Qin, Y., Mao, Y., Cao, Y., Zheng, R., Han, J., ... & Qin, Z. (2025). “Reference sample comparison method”: A new voltammetric electronic tongue method and its application in assessing the shelf life of fresh milk. Food Chemistry, 463, 141064. https://doi.org/10.1016/j.foodchem.2024.141064

28. Sowmya, N., & Ponnusamy, V. (2021). Development of spectroscopic sensor system for an IoT application of adulteration identification on milk using machine learning. IEEE Access, 9, 53979–53995. https://doi.org/10.1109/ACCESS.2021.3070558

29. Toldrá, F., & Nollet, L. M. (Eds.). (2021). Handbook of dairy foods analysis. CRC Press.

30. Wu, X., Fang, Y., Wu, B., & Liu, M. (2023). Application of near–infrared spectroscopy and fuzzy improved null linear discriminant analysis for rapid discrimination of milk brands. Foods, 12(21), 3929. https://doi.org/10.3390/foods11101465

31. Zhu, Z., & Guo, W. (2021). Recent developments on rapid detection of main constituents in milk: a review. Critical Reviews in Food Science and Nutrition, 61(2), 312–324. https://doi.org/10.1080/10408398.2020.1731417