Two assumptions dominate deep learning research on pneumonia detection from chest radiographs: that newer architectures outperform older ones, and that intra-dataset evaluation suffices to establish clinical utility. This study tested both. Nine architectures, spanning classical, efficient-scaling, and modern convolutional networks and Vision Transformers, plus a weighted soft-voting ensemble, were compared under a unified protocol on the pediatric Chest X-Ray Images dataset. None of the post-2020 architectures outperformed InceptionV3 (2016), which achieved the best individual accuracy (98.18%). The validation-weighted ensemble reached 98.52% accuracy and 99.22% pneumonia sensitivity on the internal test set; because its components were selected using test-set rankings, these values are upper-bound estimates. Bonferroni-corrected McNemar tests found no significant differences among the top-performing models. A cross-population external evaluation on an adult RSNA subset, which combines age, institutional, acquisition, and label shifts, revealed markedly different behavior: InceptionV3 retained 85.30% accuracy, whereas VGG16 fell to 59.60%, and the ensemble underperformed InceptionV3 alone. Ablation, Grad-CAM, and efficiency analyses complemented these findings. Architectural recency is not a proxy for performance, and external evaluation should be an architecture-selection criterion rather than an optional addendum.

El objetivo del estudio fue determinar si Hibernate 5.4 o MyBatis 3.4 es el más eficiente en referencia al uso del tiempo, la RAM y la CPU. Se implementó dos microservicios REST para realizar operaciones CRUD; los cuales fueron accedidos por servicios REST desarrollados con Hibernate y MyBatis invocados desde un cliente. Nuestros resultados fueron que Hibernate fue el más eficiente respecto al tiempo de procesamiento en un 509.1% y 47.7% para consultas de selección y eliminación, mientras que Mybatis en un 12.7% y 14.2% para consultas de actualización e inserción, correspondientemente. Con respecto al uso de la RAM y la CPU se determinó que MyBatis fue el más eficiente en un 55.2% y 20% respectivamente. The objective of the study was to determine whether Hibernate 5.4 or MyBatis 3.4 is the most efficient in terms of time, RAM, and CPU usage. Two REST microservices were implemented to perform CRUD operations; which were accessed by REST services developed with Hibernate and MyBatis invoked from a client. Our results were that Hibernate was the most efficient with respect to processing time at 509.1% and 47.7% for select and delete queries, while Mybatis was at 12.7% and 14.2% for update and insert queries, correspondingly. Regarding the use of RAM and CPU, MyBatis was determined to be the most efficient at 55.2% and 20% respectively.

La investigación, de enfoque cualitativo y descriptivo, propone un método de enseñanza de valores con enfoque gamificado orientado a prevenir la violencia escolar en estudiantes del nivel primario. A partir de la revisión de enfoques tradicionales e innovadores en educación en valores, se identificaron los valores clave a trabajar y se seleccionaron elementos lúdicos y principios de gamificación adecuados al contexto escolar. La propuesta metodológica se estructura en etapas que consideran el análisis del perfil del estudiante, la selección de valores prioritarios, la definición de estrategias pedagógicas, la incorporación de elementos de gamificación, el desarrollo de un prototipo de aplicación móvil y la evaluación del aprendizaje. El diseño del prototipo digital responde a la necesidad de facilitar una enseñanza interactiva, accesible y contextualizada. Los valores priorizados (respeto, empatía, autocontrol, comunicación efectiva y tolerancia) se abordan a través de dinámicas lúdicas, retos, recompensas y seguimiento del progreso individual. La evaluación del aprendizaje se plantea mediante instrumentos como listas de verificación, autoevaluaciones y retroalimentación entre pares, integrados en la propia aplicación. Este estudio constituye una base teórico-metodológica sólida para futuras implementaciones prácticas que busquen fortalecer las competencias socioemocionales en la infancia y prevenir conductas violentas desde una perspectiva formativa y tecnológica.

Inventory and condition assessment of vertical traffic signs constitutes an essential activity for road safety management, as these signs serve as the primary mechanism for regulating vehicular flow and alerting drivers to prevailing road conditions. However, current inspection procedures in Peru rely on field crews that evaluate each sign manually, thereby constraining the frequency, objectivity, and scalability of the process. This paper presents SISEVIR (Sistema de Supervisión de Señales Verticales en Infraestructura Vial), a three-stage deep learning pipeline for the automated diagnosis of vertical traffic sign condition. The first stage employs YOLO26s-seg for instance segmentation of 31 sign classes, achieving a test mAP50 of 0.9305 (box) and 0.9224 (mask). The second stage classifies each detected sign into seven deterioration states using EfficientNet-B0, optimized through a five-experiment ablation study that identified progressive offline augmentation as the most effective strategy for handling a 147:1 class imbalance (macro F1 = 0.8252; pairwise McNemar’s tests with Holm–Bonferroni correction did not confirm significance at the family-wise $\alpha =0.05$ level). The third stage integrates Qwen2-VL-2B-Instruct, a vision–language model, to generate natural-language descriptions of sign condition aligned with the MTC Manual of Traffic Control Devices for Streets and Highways. A structured evaluation by two independent raters on 35 descriptions yielded a correctness rate of 93.5% among valid responses (95% CI: 79.3–98.2%, Cohen’s $\kappa =1.00$). The system was trained and validated on a proprietary dataset of 5935 images and 6412 labeled crops collected along three routes in the Ayacucho Region (246.6 km total), with an inter-rater reliability of $\kappa =0.802$ (95% CI: 0.676–0.928). SISEVIR processes vehicular video at 30.7 FPS on an NVIDIA RTX 5080 GPU and assigns each sign a level within a four-tier condition scale (Optimal through Critical) linked to specific maintenance interventions, significantly reducing the time, cost, and personnel required compared with the manual inspection method established in the MSV-2016 Road Safety Manual.