The accurate classification of banana ripeness is essential for optimising agricultural practices and enhancing food industry processes. This study investigates the classification of banana ripeness using Machine Learning (ML) and Deep Learning (DL) techniques. The dataset consisted of 1565 high-resolution images of bananas captured over a 20-day ripening period using a Canon EOS 90D camera under controlled lighting and background conditions. High-resolution images of bananas at different ripeness stages were classified into ‘unripe’, ‘ripe’, and ‘overripe’ categories. The training set consisted of 1398 images (89.33%), and the validation set consisted of 167 images (10.67%), allowing for robust model evaluation. Various ML models, including Decision Tree, Random Forest, KNN, SVM, CNN, and VGG models, were trained and evaluated for ripeness classification. Among these, DL models, particularly CNN and VGG, outperformed traditional ML algorithms, with the CNN and VGG achieving accuracy rates of 90.42% and 89.22%, respectively. These rates surpassed those of Decision Trees (71.86%), Random Forests (85.63%), KNNs (86.83%), and SVMs (89.22%). The study points out the importance of dataset quality, model selection, and preprocessing techniques in achieving accurate ripeness classification. Practical applications of these results include optimised harvesting practices, enhanced post-harvest handling, improved consumer experience, streamlined supply chain logistics, and automation in sorting systems. These results confirm the feasibility of using deep learning for the automated classification of ripening stages, with implications for reducing postharvest losses and improving supply chain logistics. These findings have significant implications for stakeholders in the banana industry, from farmers to consumers, and pave the way for the development of innovative solutions for banana ripeness classification.

The primary objective of this study was to demonstrate the existence and uniqueness of a weak solution for a nonlinear parabolic problem with fractional derivatives for the spatial and temporal variables on a one-dimensional domain. Using the Nehari manifold method and its relationship with the Fibering maps, the existence of a weak solution for the stationary case was demonstrated. Finally, using the Arzela-Ascoli theorem and Banach's fixed point theorem, the existence and uniqueness of a weak solution for the nonlinear parabolic problem were shown.

Sustainability is understood as the dominant paradigm of the present century, where it has become a requirement for organizations. In this work, sustainable performance is explored and similar and homogeneous clusters are configured to summarize the sustainability report of a sugar company in Ecuador. Sustainability Reports were reviewed, corresponding to the period 2012 - 2022, which were analyzed in terms of social, economic and environmental components. The work had an explanatory and multivariate design. The exploration of performance through an ordinal scale, shows that they comply with the guidelines of the "triple button line", evidencing a comprehensive report, where economic aspects (GRI-200 series), social impact (GRI-400 series) are highlighted. They also report on environmental metrics (GRI-300 series). The performance evaluated to the company was carried out based on GRI indicators, from which an average performance is derived, which has been increasing in terms of improvements and number of contents, since 2012. The 18 contents were grouped into two clusters (Student's t: p-value. <0.05). The first explains 56.98% of the variance. The second cluster/factor had an explained variance of 36.81%. The cumulative total was 93.79% of variance explained, which is a high value. Because of what is left unexplained, there is a need to incorporate other variables into multivariate studies. It is necessary to explore and incorporate other variables into the multivariate studies. Other factors must be explored and incorporated in order to improve the model. Key words: environment, organization, sustainability. La sostenibilidad se entiende como el paradigma dominante del presente siglo, donde se ha constituido en un requerimiento para las organizaciones. En este trabajo se explora la problemática del desempeño sostenible con el propósito de configurar clúster similares y homogéneos que resumen el reporte de la sostenibilidad de una empresa azucarera de Ecuador. Se revisó literatura de sostenibilidad, correspondientes al periodo 2012 – 2022, que fueron analizadas en cuanto a los componentes social, económico y ambiental. El trabajo tuvo un diseño explicativo y multivariado. La exploración del desempeño mediante una escala ordinal, demuestra que cumplen con los lineamientos de la “triple botton line”, evidenciándose un reporte integral, donde se destacan los aspectos económicos (serie GRI-200), el impacto social (serie GRI-400). También reportan las métricas ambientales (serie GRI-300). El desempeño evaluado a la empresa se realizó con base a los indicadores GRI, de donde se desprende un desempeño medio, que ha venido incrementándose en cuanto a mejoras y a número de contenidos, desde el año 2012. Se agruparon los 18 contenidos en dos clústeres (t de Student: p-valor. <0.05). El primero explica el 56.98% de la varianza. El segundo clúster/factor contempló una varianza explicada de 36.81%. El total acumulado fue de un 93.79% de varianza explicada, siendo esto un valor alto. Debido a lo que se deja de explicar, surge la necesidad de incorporar otras variables a los estudios multivariados. Se impone explorar e incorporar otros factores, para poder mejorar el modelo. Palabras clave: medio ambiente, organización, sostenibilidad.

Las enfermedades cardiovasculares representan una de las principales causas de mortalidad a nivel global, y los infartos de miocardio constituyen una de las manifestaciones más críticas de esta problemática. En la región norte del Perú, la limitada infraestructura hospitalaria y el acceso insuficiente a diagnósticos especializados incrementan la vulnerabilidad de la población. El presente estudio propone el desarrollo de un modelo predictivo basado en Redes Neuronales Artificiales (RNA) para la detección temprana de infartos. Se trabajó con datos secundarios de la encuesta demográfica y de salud familiar del periodo 2005–2024, con un total de 573,080 registros que incluyen factores de riesgo como hipertensión, diabetes, obesidad, tabaquismo y consumo de alcohol. La metodología contempló la limpieza, integración y normalización de datos, seguida de la implementación de un modelo de RNA en Python, validado mediante métricas de precisión, sensibilidad y especificidad. Los resultados preliminares evidencian una precisión predictiva superior al 90%, lo que respalda la viabilidad del uso de inteligencia artificial en la medicina preventiva, particularmente en escenarios caracterizados por una alta demanda asistencial.

Existencia de solución débil para un problema no lineal con el operador p-Laplaciano fraccionario