AI-Enabled Linear Regression Model for Spectroscopic Milk Adulteration Analysis

Year : 2026 | Volume : 15 | Issue : 01 | Page : 28 41
    By

    Mrs.Vrishali M Patil,

  • Dr. Savita Bhosale,

  1. Research Scholar, Department of EXTC Engineering RAIT, D. Y. Patil Deemed to be University, Navi Mumbai, India
  2. Professor, Department of Electroniocs Engineering,R.A.I.T, D. Y. Patil Deemed to be University, Navi Mumbai, India

Abstract

Milk adulteration poses a serious threat to public health and quality assurance in the dairy industry. This requiring rapid, reliable, and non-destructive detection techniques. This study presents a linear regression-based analytical model for identifying and quantifying milk adulteration using spectroscopic data. Spectral measurements of milk samples, including both pure and adulterated variants were acquired using spectroscopic techniques at relevant wavelengths.Blending of other components in  pure milk , is specifically called milk adulteration which is dangerous in high amounts to milk quality and consumer protection. The current study is presenting the linear regression-based detection of water adulteration in milk with Near-Infrared (NIR) spectroscopy. We tested a sample of 100-200 milk samples with different quantities of water or other additives added, where spectral absorbance patterns were used as predictors. Linear regression models were built to establish the relationship of the NIR spectral properties with proportions of adulteration. The results showed high predictive accuracy, measuring even small quantities of water and other common mixtures in milk precisely. The effective method explains the potential of regression-based statistical modeling as an efficient, cost-effective and practical solution to quality control in the Artificial Intelligence (AI) methods to improve the precision, accuracy and speed of adulteration detection.

Keywords: Crop disease detection, deep learning, IoT in agriculture, machine learning, precision agriculture, sustainable farming, yield prediction

[This article belongs to Research & Reviews : Journal of Food Science & Technology ]

How to cite this article:
Mrs.Vrishali M Patil, Dr. Savita Bhosale. AI-Enabled Linear Regression Model for Spectroscopic Milk Adulteration Analysis. Research & Reviews : Journal of Food Science & Technology. 2026; 15(01):28-41.
How to cite this URL:
Mrs.Vrishali M Patil, Dr. Savita Bhosale. AI-Enabled Linear Regression Model for Spectroscopic Milk Adulteration Analysis. Research & Reviews : Journal of Food Science & Technology. 2026; 15(01):28-41. Available from: https://journals.stmjournals.com/rrjofst/article=2026/view=236832


References

  1. Nagraik R, Sharma A, Kumar D, Chawla P, Kumar AP. Milk adulterant detection: conventional and biosensor based approaches: a review. Sensing Bio-Sensing Res. 2021;33:100433. doi: 10.1016/j.sbsr.2021.100433.
  2. Hosseini E, et al. Application of genetic algorithm and multivariate methods in detection and measurement of milk-surfactant adulteration by attenuated total reflection and near-infrared spectroscopy. J Sci Food Agric. 2020. doi: 10.1002/jsfa.10894.
  3. Handford C, et al. Impacts of milk fraud on food safety and nutrition with special emphasis on developing countries. Compr Rev Food Sci Food Saf. 2016;15(1):130–142. doi: 10.1111/1541-4337.12181.
  4. Nasir A, et al. Impact of adulteration on physico-chemical characteristics of marketed raw milk. Pak-Euro J Med Life Sci. 2022. doi: 10.31580/pjmls.v5i2.2608.
  5. Mhapsekar R, et al. Edge-AI implementation for milk adulteration detection. In: Proc IEEE Global Conf Artif Intell Internet Things (GCAIoT); 2022. p. 108–113. doi: 10.1109/GCAIoT57150.2022.10019173.
  6. Farah JS, et al. Differential scanning calorimetry coupled with machine learning technique: an effective approach to determine the milk authenticity. Food Control. 2021;121:107585. doi: 10.1016/j.foodcont.2020.107585.
  7. Botelho BG, et al. Development and analytical validation of a screening method for simultaneous detection of five adulterants in raw milk using mid-infrared spectroscopy and PLS-DA. Food Chem. 2015;181:31–37. doi: 10.1016/j.foodchem.2015.02.077.
  8. Pal JB, Mistry A, Bandyopadhyay D, Biswas B, Bhattacharya S. Adulteration of milk identification using ionic polymer metal composite as sensor. IEEE Sens Lett. 2023;7(3). doi: 10.1109/LSENS.2023.3247426.
  9. Zhang W, Kasun LC, Wang QJ, Zheng Y, Lin Z. A review of machine learning for near-infrared spectroscopy. Sensors (Basel). 2022;22(24):9764. doi: 10.3390/s22249764.
  10. Galindo C, et al. Bovine milk microwave dielectric response to pregnancy. In: Proc 13th Int Conf Electromagn Wave Interact Water Moist Subst (ISEMA); 2021. p. 1–4. doi: 10.1109/ISEMA49699.2021.9508329.
  11. Khenwar M, Vishnoi S, Sisodia A. An assessment of milk adulteration IoT based model to identify the quality of milk using LabVIEW. In: Proc 11th Int Conf Syst Model Adv Res Trends (SMART); 2022. p. 868–873. doi: 10.1109/SMART55829.2022.10047364.
  12. Dave A, Banwari D, Srivastava S, Sadistap S. Optical sensing system for detecting water adulteration in milk. In: Proc IEEE Global Humanitarian Technology Conf (GHTC); 2016. p. 634–639. doi: 10.1109/GHTC.2016.7857345.
  13. Wadalkar NM, Mudhalwadkar RP, Sulkekar AA. Development of electrical impedance sensor system for milk adulteration (A1 and A2). In: Proc 3rd Int Conf Trends Electron Informatics (ICOEI); 2019. p. 107–109. doi: 10.1109/ICOEI.2019.8862733.
  14. Ghayoumi M. Generative adversarial networks in practice. 1st ed. Boca Raton: Chapman and Hall/CRC; 2023. doi: 10.1201/9781003281344.
  15. Kunes R, et al. In-line technologies for the analysis of important milk parameters during the milking process: a review. Agriculture. 2021;11(3):239. doi: 10.3390/agriculture11030239.
  16. Dave A, Banwari D, Mansinghani S, Srivastava S, Sadistap S. Ultrasonic sensing system for detecting water adulteration in milk. In: Proc IEEE Region 10 Conf (TENCON); 2016. p. 2228–2231. doi: 10.1109/TENCON.2016.7848424.
  17. Natarajan S, Ponusamy V. A review on quantitative adulteration detection in milk. In: Proc Smart Technologies, Communication and Robotics (STCR); 2021. p. 1–4. doi: 10.1109/STCR51658.2021.9588800.
  18. Alagumeenaakshi M, Ajitha S, Sathika J, Navaneethakrishnan R. Milk adulteration monitoring. In: Proc Int Conf Advancements Electr Electron Commun Comput Autom (ICAECA); 2021. p. 1–5. doi: 10.1109/ICAECA52838.2021.9675630.
  19. Tapadar A, Adhikary A. High sensitivity milk adulteration detector using fractional order Colpitts oscillator. In: Proc IEEE Conf AgriFood Electronics (CAFE); 2023. p. 85–88. doi: 10.1109/CAFE58535.2023.10292088.
  20. Patari S, Mahapatra PS. A point of care sensor for milk adulteration detection. In: Proc IEEE Sensors; 2021. p. 1–4. doi: 10.1109/SENSORS47087.2021.9639690.
  21. Ghodinde KA, Chaskar UM. Quantification of urea adulteration with impedance spectroscopy in cow milk. In: Proc 6th Int Conf Convergence in Technology (I2CT); 2021. p. 1–5. doi: 10.1109/I2CT51068.2021.9418154.
  22. Chakraborty M, Biswas K. Limit of detection for five common adulterants in milk: a study with different fat percent. IEEE Sens J. 2018;18(6):2395–2403. doi: 10.1109/JSEN.2018.2794764.
  23. Pugazhenthi K, Sengamalam A, Ganesan B. Milk quality monitoring system using IoT. In: Proc Int Conf Sustainable Computing Smart Systems (ICSCSS); 2023. p. 1096–1098. doi: 10.1109/ICSCSS57650.2023.10169262.
  24. Salmaz U, Islam T. A dynamic milk quality capacitive sensing system for detection of detergent. In: Proc IEEE Int Conf Communication Systems Network Technologies (CSNT); 2024. p. 374–379. doi: 10.1109/CSNT60213.2024.10546082.
  25. Bose A, Tapadar A, Kumar M, Adhikary A. Detection of urea in adulterated milk with 3% fat using disposable paper sensor. IEEE Sens Lett. 2024;8(8):4502004. doi: 10.1109/LSENS.2024.3417283.
  26. Deshpande A, Deshpande S, Dhande S. NIR spectroscopy based milk classification and purity prediction. In: Proc IEEE Pune Section Int Conf (PuneCon); 2021. p. 1–5. doi: 10.1109/PuneCon52575.2021.9686473.
  27. Chakraborty M, Biswas K. Milk tester: simultaneous detection of fat content and adulteration. IEEE Trans Instrum Meas. 2020;69(5):2468–2476. doi: 10.1109/TIM.2019.2955796.
Regular Issue Subscription Original Research
Volume 15
Issue 01
Received 01/01/2025
Accepted 07/01/2026
Published 13/02/2026
Publication Time 408 Days
86

Login


My IP

PlumX Metrics