A supervised machine learning approach for the prediction of antioxidant activities of seed.

This research aimed at modelling and predicting the antioxidant activities of seed extract using four (4) data-driven models. Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbour (k-NN), and Decision Tree (DT) were used as modelling algorithms for the construction of a non-linear empirical model to predict the antioxidant properties of seed extract. Datasets for the modelling operation were obtained from a Box Behnken design while the hyperparameters of the ANN, SVM, k-NN and DT were determined using a 10-fold cross-validation technique.

Understanding how different modification processes affect the physiochemical, functional, thermal, morphological structures and digestibility of cardaba banana starch.

In this study, starch was isolated from cardaba banana starch and was subjected to modification by heat-moisture treatment, citric acid, octenyl succinic anhydride, and sodium hexametaphosphate. Both the native and modified cardaba banana starches were examined for chemical, functional, pasting, thermal, morphological, structural, and antioxidant properties, as well as in vitro starch digestibility. Modification significantly influenced the properties of the cardaba banana starch.