In 2020, there were more than 1.2 million new skin cancer diagnoses, and melanoma was the most recurrent type of cancer. On the other hand, melanoma is the least common but most serious form of skin cancer affecting both men and women. This work aims to assemble classification models to detect a case of melanoma with high accuracy based on a Convolutional Neural Networks system. The methodology considers training 21 models for image classification, with the best assembly performance of EfficientNet and VGG-19 architectures, the data augmentation technique was used to the images to improve its performance. The results show 92.85% of accuracy, 71.50% of sensitivity, and 94.89% of specificity, with an improvement of 0.06% in accuracy and specificity. The assembly of the classification models achieved higher accuracy in melanoma skin cancer image classification.
This systematic literature review examines the rapid growth of research on the use of drones applied to smart agriculture, a key field for the digital and sustainable transformation of the agricultural sector. The study aimed to synthesize the current state of knowledge regarding the application of drones in smart agriculture by applying the Kitchenham protocol (SLR), complemented with Petersen’s systematic mapping (SMS). A search was conducted in high-impact academic databases (Scopus, IEEE Xplore, Taylor & Francis Online, Google Scholar, and ProQuest), covering the period 2019–2025 (July). After applying the inclusion, exclusion, and quality criteria, 73 relevant studies were analyzed. The results reveal that 90% of the publications appear in Q1 journals, with China and the United States leading scientific production. The thematic analysis identified “UAS Phenotyping” as the main driving theme in the literature, while “precision agriculture,” “machine learning,” and “remote sensing” were the most recurrent and highly interconnected keywords. An exponential increase in publications was observed between 2022 and 2024. The review confirms the consolidation of drones as a central tool in digital agriculture, with significant advances in yield estimation, pest detection, and 3D modeling, although challenges remain in standardization, model generalization, and technological equity. It is recommended to promote open access repositories and interdisciplinary studies that integrate socioeconomic and environmental dimensions to strengthen the sustainable adoption of drone technologies in agriculture.
Las organizaciones incurren en pérdidas económicas debido al fracaso de la gestión de las Tecnologías de la Información (TI) tradicionales, lo cual exige la implementación de tecnologías más eficientes como la Inteligencia Artificial. El objetivo de esta investigación fue implementar un Prototipo de Asistente Personal Virtual basado en Inteligencia Artificial aplicado en las oficinas de TI del Sector Público, a fin de asistir a los líderes TI en la Gestión de Proyectos. Se realizó en tres etapas: Revisión general del proceso de Gestión de los proyectos de TI, diseño e implementación del prototipo y evaluación del Prototipo desarrollado. Como resultado se implementó un prototipo, desarrollado con lenguaje de programación Python, sobre una plataforma Microsoft Windows 10, que interactúa con voz y con lenguaje natural y cumple tres funciones: Creación un Proyecto de TI, Generar registro de consultas y observaciones de proveedores en estudio de mercado, Generar registro de Comité de Selección. El prototipo asiste al líder TI en la gestión de Proyectos, simplificando y optimizando el tiempo y recursos en las actividades de organización, captura y registro de la información de los Proyectos TI en las Oficinas de TI de las organizaciones del Sector Público.