In this study (purchase required), the authors used one-class and multiclass methods applied to ATR-FTIR data to classify a set of 80 diluted and undiluted soy milks. The unequal dispersed classes (UNEQ), soft independent modeling of class analogy (SIMCA), data driven SIMCA (DD-SIMCA), and one-class random forest (OC-RF) methods were used for one-class modeling. Models were constructed using the non-adulterated samples as target class and the adulterated samples as non-target class. The k-nearest neighbors (k-NN), partial least squares discriminant analysis (PLS-DA), dual class random forest (DC-RF), and dual class random forest with Monte Carlo sampling (DC-RF-MC) methods were used for multiclass modeling.
For k-NN and PLS-DA, samples were organized into four classes (non-adulterated samples, adulterated with 5% v∙v-1, 10% v∙v-1, and 20% v∙v-1 of water). DC-RF models used the same class settings as one-class models.
The authors report that the results show the feasibility of ATR-FTIR and chemometrics models to identify adulteration of soy milk by diluting with water at levels from 5% upwards.
Photo by Mae Mu on Unsplash
Comments