Search Results (3)

Automatic classification of Ataulfo mango (Mangifera indica L.) ripeness is essential to ensure consistent quality, standardize post-harvest processes, and reduce the subjectivity of traditional visual inspection, which is unreliable and error-prone. This paper aims to develop a computationally efficient image classification system for Ataulfo mango ripeness by combining explicit color and texture feature extraction with a traditional machine learning model, thereby reducing the high computational costs typically associated with deep convolutional architectures. For this purpose, a dataset containing 10,400 images was created and divided into four maturity categories: green-ripe, partially ripe, firm-ripe, and soft-ripe. We select an optimal Multilayer Perceptron trained on compact 33-dimensional feature vectors and compare its performance with classical machine learning algorithms and pretrained deep neural networks, including MobileNetV2, MobileNetV3, and ResNet18. Our proposal achieves an accuracy of 0.8821, a macro-F1 score of 0.8784, and an AUC of 0.9751, which are better than those of classical classifiers and MobileNet-family models, while reducing computational cost by three orders of magnitude (GFLOPs). The ResNet18 model achieved a 3.56% relative improvement in macro-F1 score compared to our proposal, but its computational cost increased by four orders of magnitude in GFLOPS. In all evaluated architectures, the remaining classification errors occur between adjacent maturity stages and likely reflect the visual similarity inherent in the continuous ripening process. These findings demonstrate that manual feature engineering and model selection via hyperparameter tuning remain highly competitive and more sustainable for low-cost edge implementations in agriculture. Full article

Monitoring moisture content in agricultural products during the drying process is critical for ensuring quality, preserving nutritional value, and optimizing energy consumption. This study presents the design and implementation of an optical fiber sensor based on multimode interference (MMI) for non-destructive detection of moisture content in mango (Mangifera indica L., cv. Ataulfo) and papaya (Carica papaya) slices during convective drying at 57 °C. Two sensors were designed and fabricated: one operates in the 975 nm range and the other in the 1414.25 nm range. These sensors detect variations in the refractive index caused by moisture loss, which directly affects the MMI spectral response. The sensor output was correlated with reference gravimetric measurements, demonstrating a dependence in tracking the output power as a function of the reduction in humidity over time. The results confirm the feasibility of the MMI-based optical fiber sensor as a reliable tool for in situ monitoring of drying dynamics in tropical fruits, offering potential applications in agri-food processing and quality control. Full article

Mango (Mangifera indica cv. Ataulfo) peel contains bound phenolics that may be released by alkaline or acid hydrolysis and may be converted into less complex molecules. Free phenolics from mango cv. Ataulfo peel were obtained using a methanolic extraction, and their cellular antioxidant activity (CAA) and permeability were compared to those obtained for bound phenolics released by alkaline or acid hydrolysis. Gallic acid was found as a simple phenolic acid after alkaline hydrolysis along with mangiferin isomers and quercetin as aglycone and glycosides. Only gallic acid, ethyl gallate, mangiferin, and quercetin were identified in the acid fraction. The acid and alkaline fractions showed the highest CAA (60.5% and 51.5%) when tested at 125 µg/mL. The value of the apparent permeability coefficient (Papp) across the Caco-2/HT-29 monolayer of gallic acid from the alkaline fraction was higher (2.61 × 10⁻⁶ cm/s) than in the other fractions and similar to that obtained when tested pure (2.48 × 10⁻⁶ cm/s). In conclusion, mango peels contain bound phenolic compounds that, after their release, have permeability similar to pure compounds and exert an important CAA. This finding can be applied in the development of nutraceuticals using this important by-product from the mango processing industry. Full article