Differential scanning calorimetry coupled with machine learning technique: An effective approach to determine the milk authenticity

Differential scanning calorimetry (DSC) coupled with machine-learning tools (random forest, gradient boosting machine, and multilayer perceptmn, RF, GBM, MLP) were used to detect adulteration of raw bovine milk (formaldehyde, whey, urea, and starch). Adulterated samples presented a different DSC profile from raw milk. GBM and MLP were able to classify 100% of adulterated samples, whereas RF showed optimal performance with recognition and prediction capability of 100% and 88.5%, respectively. Overall, peak temperature of crystallization was the most important discriminating predictor for GBM and RF models, whereas peak temperature of boiling followed by onset temperature of crystallization and onset temperature of boiling were the most important predictors for MLP model. The detection of adulteration in milk has a multidimensional approach and DSC associated with machine-learning methods present an interesting perspective with practical potential to be adopted by the dairy industry.

Automated summary

The study successfully detected adulteration in raw bovine milk using DSC coupled with machine-learning tools, with GBM and MLP achieving 100% classification capability and RF showing optimal performance as well. Different models had varying important predictors, showcasing a multidimensional approach with practical potential for adoption by the dairy industry.