Assessing nutritional probing and storage stability of functional Aloe vera (Aloe barbadensis) based guava jam: a machine learning approach for predictive modelling

This research aimed to explore the influence of nutritional adjustments and storage stability on a functional, reduced-calorie guava jam incorporating Aloe vera. Over two months, comprehensive analysis assessed physicochemical properties, sensory traits, microbial stability, and shelf-life. The addition of Aloe vera gel resulted in significant improvements in pH (3.00 to 3.65), total soluble solids (40.10 to 42.20°Brix), antioxidant activity (36.85% to 81.09%), moisture content (29.48% to 38.82%), water activity (0.78 to 0.84), ash content (0.29% to 0.45%), fat content (0.14% to 0.19%), fibre content (1.05% to 1.86%), and the colour values. Moreover, b* scores for colour indication improved from 15.09 to 18.86. Texture attributes of cohesiveness and firmness improved significantly. Sensory evaluation favoured the T2 variant (20% Aloe vera gel), suggesting it as the optimal formulation. Furthermore, artificial neural networks (ANNs), a technique of machine learning, were utilised to predict guava jam behaviour, with 99% accuracy. The study discovered substantial changes in pH, total soluble solids, antioxidant activity, moisture content, and textural qualities, indicating that Aloe vera supplementation could improve guava jam quality and shelf-life. The results of ANN predictions about antioxidants and cohesiveness provide information about the product's performance during storage.