Objective: Late blight disease, caused by Phytophthora infestans, represents a critical threat to tomato cultivation, significantly affecting its quality and productivity. This study aimed to develop a technological tool for the early and precise detection of tomato disease in a controlled agricultural environment using machine learning (ML) techniques and digital image processing.. Methodology: A total of 3560 foliar images encompassing three severity levels of Phytophthora infestans were acquired. The Segment Anything Model (SAM) was implemented as a preprocessing step to isolate the biological tissue and eliminate chromatic background noise. Three classifiers were evaluated using a unified Monte Carlo cross-validation framework (10 iterations, 70/30 split): SVM and KNN, based on global chromatic descriptors (HSV/YIQ and PCA), compared with a CNN that extracts local spatial topologies. Results: Within the evaluated dataset, the convolutional neural network (CNN) and the local distance-based model (KNN) achieved classification metrics exceeding 98%, significantly outperforming the global color-based baseline (SVM, 79%). By evaluating the localized spatial morphology of the necrotic lesions, the CNN architecture effectively mitigated misclassifications in extreme severity phenotype. Consequently, these high classification metrics must be interpreted as an upper performance bound, strictly constrained to the ideal and controlled conditions of the greenhouse setup. Conclusions: The developed tool demonstrates high potential for automated disease diagnosis in tomatoes, contributing to phytosanitary management through emerging technologies. This study highlights ML’s role as a driver of innovation for more precise, efficient, and sustainable agriculture.
Objetivo: las redes sociales, como herramientas emergentes de las últimas tres décadas, han evolucionado en paralelo con Internet. Estas plataformas ofrecen formas de interacción que pueden derivar en distracciones positivas como negativas, según el uso que se les dé. En el ámbito educativo, un uso inadecuado de estas plataformas digitales puede generar problemas de distracción y afectar negativamente el aprendizaje. En este contexto, la presente investigación desarrolla un modelo predictivo basado en minería de datos y aprendizaje automático, con el objetivo de identificar el grado de distracción en el proceso de enseñanza-aprendizaje.Metodología: la base de conocimiento, construida a partir de una encuesta aplicada a más de 1000 estudiantes de educación superior, proporciona la información necesaria para entrenar algoritmos de aprendizaje automático capaces de predecir la probabilidad de que un estudiante sufra distracciones debido al uso de las redes sociales.Resultados: los resultados obtenidos muestran que el modelo es capaz de detectar adecuadamente el 80 % de los casos de distracción, aunque existe margen para mejorar estos resultados mediante ajustes en la base de conocimiento.Conclusiones: los hallazgos actuales demuestran un buen rendimiento en la predicción de distracciones relacionadas con el uso de las plataformas digitales, lo que permitiría anticipar el bajo rendimiento de estudiantes y proponer estrategias de mejora.
Objective: To design and simulate an electric kart that maximizes energy efficiency for racing. Methodology: The project entitled “Design and simulation of an electric kart that maximizes energy efficiency for racing” was developed using a quantitative, descriptive, and experimental virtual approach based on the construction of mathematical models, computer-aided design, and simulation using specialized software. The study is part of an applied research design, as it seeks to generate a technical solution to a specific problem: increasing energy efficiency in electric racing karts. Likewise, the research is based on a deductive method, starting from theories of vehicle dynamics and energy efficiency, to arrive at the validation of an optimized model through simulations. Results: The results validated the feasibility of the proposed design and provided invaluable insights for adjustments and enhancements. So they found that putting the electric propulsion system into the kart is okay. The kart still works well with this system. The electric propulsion system does not make the kart too heavy. This is important because the SuperKart category stays that the kart cannot weigh more than 240 kg. The electric propulsion system helps with this rule. The kart with the electric propulsion system is still under the 240 kg limit, for the SuperKart category. Conclusions: Through numerical simulations conducted in Matlab, the eKart performance was meticulously optimized, focusing on speed, autonomy, and energy efficiency. The outcomes reveal a substantial enhancement in the maximum speed attained, selection of the optimal reduction (Ntf), and increased autonomy without compromising energy consumption. The computer simulations provided comprehensive insights into the startup and operation of the components comprising the electric kart propulsion system during races, where the vehicle achieves a speed of 248 km/h in merely 34 seconds.
Contexto: los sistemas de tracción eléctrica modernos demandan convertidores de potencia capaces de operar bajo condiciones dinámicas exigentes, garantizando un suministro de energía estable, eficiente y de calidad. Uno de los principales problemas en estos sistemas es la distorsión armónica introducida por el inversor, la cual afecta negativamente el funcionamiento de la máquina. Objetivo: implementar un inversor multinivel en cascada trifásico con optimización armónica para aplicaciones de tracción eléctrica. Metodología: la metodología consta de la definición de la topología del inversor, la estructuración de una estrategia de conmutación complementada con un modelo de optimización y, finalmente, la validación mediante pruebas funcionales del prototipo en vacío. Resultados: los resultados permiten identificar formas de tensión con niveles definidos, aproximación senoidal, correctamente desfasadas entre sí y equilibradas en términos de tensión eficaz. Asimismo, se registraron valores de THD entre 1.2 % y 1.6 % para tensiones de fase, y entre 1 % y 1.2 % para tensiones de línea, mediante pruebas experimentales en vacío. Conclusiones: la topología de inversor multinivel en cascada trifásico, junto con un modelo de optimización armónica mediante algoritmos genéticos, constituye una solución viable al problema del alto contenido armónico en convertidores de potencia para sistemas de tracción. Financiamiento: este estudio hace parte de un proyecto de investigación aprobado por la Universidad de Pamplona como trabajo final de maestría, con financiación de recursos propios y apoyo institucional.
Objective: This article examines the thematic evolution and intellectual structure of research on intangible assets in micro, small, and medium-sized enterprises (MSMEs) through a comparative approach between Latin America and the international context. Its aim is to identify the main theoretical streams, regional gaps, and research dynamics that shape this field, highlighting both the convergences and divergences between the two contexts. Methodology: A mixed methodology was adopted, combining bibliometric techniques, such as co-citation analysis and thematic evolution, with a qualitative content review. The Scopus and Web of Science databases served as data sources, yielding a total of 683 documents published up to 2024, 54 of which correspond to Latin American affiliations. Results: The results reveal lower conceptual and methodological density in Latin American scientific production, characterized by a fragmented structure and a limited presence of consolidated theoretical frameworks. Nevertheless, emerging regional themes were identified that position intangible assets as strategic tools for productive transformation. Conclusions: The study concludes that Latin America is undergoing a delayed yet progressive alignment with the global agenda, and it highlights the need to strengthen context-specific frameworks that articulate global conceptual richness with regional realities.
