Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Aug 26, 2025

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice
04:56

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice

Published on: March 28, 2025

781

A machine learning proposal method to detect milk tainted with cheese whey.

Juliana S Lima1, Daniela C S Z Ribeiro1, Habib Asseiss Neto2

  • 1Department of Food Technology and Inspection, School of Veterinary Medicine, Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil 31270-901.

Journal of Dairy Science
|October 7, 2022
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Buffalo milk quality: A study of seasonal influence on composition and somatic cell count.

Journal of dairy science·2024
Same author

Profile of lactic acid bacteria (MALDI-TOF-MS) and physico-chemical and microbiological characteristics of the raw milk and fresh artisanal cheese from Serra Geral, Minas Gerais, Brazil.

Food research international (Ottawa, Ont.)·2024
Same author

Determination of the lactose content in low-lactose milk using Fourier-transform infrared spectroscopy (FTIR) and convolutional neural network.

Heliyon·2023
Same author

A System for Structuring, Storage and Georeferenciation of Dengue Vector Surveillance Data.

Studies in health technology and informatics·2022
Same author

In Silico Laboratory Experiments Using Statistical Model Checking: A New Model of the Palytoxin-Induced Pump Channel as Case Study.

IEEE/ACM transactions on computational biology and bioinformatics·2020
Same author

On the utilization of deep and ensemble learning to detect milk adulteration.

BioData mining·2019
This summary is machine-generated.

Detecting cheese whey in milk fraud is crucial. Fourier-transform infrared (FTIR) spectroscopy combined with machine learning offers a highly accurate and efficient screening method for identifying adulterated milk, achieving over 97% accuracy.

Area of Science:

  • Food Science
  • Analytical Chemistry
  • Machine Learning

Background:

  • Cheese whey addition to milk is a prevalent fraud with significant economic and safety implications.
  • Current detection methods are costly and time-consuming, limiting their use in routine screening.
  • Fourier-transform infrared (FTIR) spectroscopy generates extensive data suitable for machine learning analysis.

Purpose of the Study:

  • To evaluate FTIR spectroscopy coupled with machine learning for detecting cheese whey adulteration in milk.
  • To assess the efficacy of classification tree (CART) and multilayer perceptron neural networks for this purpose.

Main Methods:

  • 520 raw milk samples were adulterated with varying concentrations of cheese whey (1-30%) and stored under different temperature and time conditions.
Keywords:
artificial neural networkscheese wheyfraudinfrared spectroscopymachine learning

More Related Videos

Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit
07:38

Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit

Published on: December 16, 2015

12.5K
A Method for Targeted 16S Sequencing of Human Milk Samples
09:09

A Method for Targeted 16S Sequencing of Human Milk Samples

Published on: March 23, 2018

10.0K

Related Experiment Videos

Last Updated: Aug 26, 2025

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice
04:56

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice

Published on: March 28, 2025

781
Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit
07:38

Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit

Published on: December 16, 2015

12.5K
A Method for Targeted 16S Sequencing of Human Milk Samples
09:09

A Method for Targeted 16S Sequencing of Human Milk Samples

Published on: March 23, 2018

10.0K
  • FTIR spectroscopy was used to analyze samples and predict key components (fat, protein, lactose, etc.) and freezing point.
  • Predicted FTIR data served as input features for CART and multilayer perceptron machine learning models.

    • Main Results:

    • Both CART and multilayer perceptron models achieved high accuracy, reaching 96.2% and 97.8%, respectively.
    • Precision, sensitivity, and specificity for both methods exceeded 95%.
    • The combined FTIR and machine learning approach effectively differentiated authentic milk from whey-adulterated samples.

    Conclusions:

    • FTIR spectroscopy combined with machine learning provides a highly efficient method for detecting cheese whey adulteration in milk.
    • This approach shows potential as a high-performance screening process for milk quality laboratories.
    • Accurate prediction of milk composition and freezing point using FTIR is key to successful fraud detection.