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

This research aimed at modelling and predicting the antioxidant activities of Amaranthus viridis 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 Amaranthus viridis 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. Among the Machine Learning algorithms, DT was observed to exhibit excellent performance and outperformed other Machine Learning algorithms in predicting the antioxidant activities of the seed extract, with a sensitivity of 0.867, precision of 0.928, area under the curve of 0.979, root mean square error of 0.184 and correlation coefficient of 0.9878. It was closely followed by ANN which was used to analyze and explain in detail the effect of the independent variables on the antioxidant activities of the seed extracts. This result affirmed the suitability of DT in predicting the antioxidant activities of Amaranthus viridis.

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. Cross-linking treatment improved the water, oil absorption, alkaline hydration capacity, swelling power, solubility and paste clarity of the starch. The final viscosity of the banana starch paste was increased alongside succinic anhydride modification which in turn enhanced the suitability of the starch in the production of high viscous products. Both FTIR spectra and X-ray diffractograms confirmed the starch had a C-type starch which was not affected by modification. Modification led to a decrease in relative crystallinity of the starch with succinylation having the maximum effect. The starch fractions; both SDS and RS significantly increased due to modification while the hydrolysis and glycemic index of the starch were significantly decreased by chemical modification. In conclusion, both physical and chemical modification of cardaba banana starch produced a starch that can serve as functional food or functional food ingredients.

Modeling of thin layer drying characteristics of blanch-assisted water yam (Dioscorea alata) slices

The thin layer drying characteristics of blanch-assisted water yam slices were investigated with respect to its un-blanched water yam slices in a convective hot air oven. The yam slices (diameter 4 cm; thickness 0.8 cm) were dried at temperatures 50, 60 and 70 °C, respectively with a constant air velocity of 0.13 m/s. The drying data obtained were fitted into six existing drying models: Page, Newton, Midilli, Henderson and Pabis, Logarithmic and Diffusion model. Non-linear regression analysis was used to determine the model parameters; the coefficient of determination (R2) and standard error of estimates (SEE) in order to determine the model best fit. The study showed that the drying process occurred in the falling rate drying period. The blanch-assisted slices had a faster drying rate than the un-blanched yam slices. Among the models, the diffusion model gave the overall best fit for the drying data obtained. The effective moisture diffusivity ranged from 3.18×10-8 to 4.47×10-8 m2/s for the blanch-assisted slices and from 4.73×10-8 to 7.33×10-8 m2/s for the un-blanched slices. The activation energies of the blanch-assisted and un-blanched yam slices were 15.5 kJ/mol and 20.1 kJ/mol, respectively. These processing conditions obtained for water yam flour would be suitable for its process design and control thereby enhancing its utilization and overall acceptability.

Acetylation of Amaranthus viridis starch: Modeling and process parameters optimization

The optimum reaction conditions for the derivation of acetylated (esterified) starch using response surface methodology (RSM) and artificial neural network (ANN) were studied. All the independent variables (starch solids, acetic anhydride concentration, and reaction time) were of significant (p < .05) importance in achieving esterified starch of Amaranthus viridis. Optimum conditions of 152.46 g of starch, 11 ml of acetic anhydride and time of 2.92 min with corresponding acetyl content and degree of substitution (DS) of 1.74% and 0.06, respectively, were established for ANN. The RSM gave optimum conditions of 149.57 g (starch), 10.38 ml (acetic anhydride) and 3 min (time) with corresponding acetyl content and DS of 1.61% and 0.06, respectively. The order of priority of the process variables was established as acetic anhydride (42.59%), starch solids (33.90%), and reaction time (23.51%). The results provided useful information on development of economic and efficient acetylation process for modification of A. viridis starch.

Comparative analysis of physico-chemical properties and amino acids profile of three tropical maize hybrid cultivars in Nigeria

Purpose

The purpose of this study was to compare the physico-chemical properties and amino acid profile of three maize hybrid cultivars grown in Nigeria.

Design/methodology/approach

Two normal maize endosperm varieties, yellow SUWAN-ISR (YNM) and white ART/98/SW05-OB-WC (WNM), and one yellow QPM variety, TZE-POP-DT-STR-QPM (YQPM), were selected for the study. Physico-chemical properties, physical tests, proximate composition analysis, functional properties and characteristics and amino acid profile tests were carried out on the grains using standard methods.

Findings

Protein was significantly higher (p < 0.05) in YQPM (10.49 per cent) than in normal endosperm, YNM (8.83 per cent) and WNM (8.50 per cent). Amino acid profile of the grains revealed that total amino acid of YQPM (94.67 g/100 g of protein) and essential amino acid of YQPM (39.070) were the highest among the three, with highest significantly different value of tryptophan (0.388 g/100 g of protein) at p < 0.05. The cooking quality of YQPM was found to be better than the other two, with highest hydration capacity and increase in volume after cooking (90.8 ± 0.01 g/1000 grains and 147.53 ± 0.02 per cent).

Originality/value

YQPM will be highly beneficial in the tropics, where maize is grown as the major staple food to reduce hunger and malnutrition because of its amino acid balance and its better cooking quality.

Effect of addition of ripe bananas on some physico-chemical properties of maize 'extract'

Flour mixes obtained by the addition of banana pulp in various proportions (0-50%) to maize 'extracts' were evaluated for some quality characteristics. All the mixes had significantly lower values of crude protein, fat and water-holding capacity. Gelation, however, significantly increased the water-holding capacity in all cases. The ash content, titratable acidity and total sugars increased tremendously with an increase in the level of banana substitution. While both Adam's consistency values and equilibrium moisture content decreased with an increase in the level of banana substitution, the syneresis values did not show any consistent pattern. The consistently low moisture content and the results of the moisture sorption isotherms suggest a good storage stability of all the mixes, especially when kept under conditions of water activity of 0.30 and below, and their possible suitability for baked products.