This study compares the performance of three YOLO-based object detection models—YOLOv3, YOLOv5, and YOLOv8—for vehicle detection and classification at an urban intersection in Montería, Colombia. Recordings from five consecutive days, spanning three time slots, were used, totaling approximately 135,000 frames with variability in lighting and weather conditions. Frames were preprocessed by maintaining the aspect ratio and were normalized according to each model. The evaluation employed models pre-trained on COCO, without fine-tuning, enabling an objective assessment of their generalization capacity. Precision, recall, F1-score, and mAP@0.5 were computed globally and by vehicle class. YOLOv5 achieved the best balance between precision and recall (F1-score = 0.78) and the highest mAP (0.63), while YOLOv3 showed lower recall and mAP, and YOLOv8 performed competitively but slightly below YOLOv5. Cars and motorcycles were the most robust classes, whereas bicycles and trucks showed greater detection challenges. Visual evaluation confirmed stable performance on cloudy days and in light rain, with reduced accuracy under sunny conditions with high contrast. These findings highlight the potential of modern YOLO architectures for intelligent urban traffic monitoring and management. The generated dataset constitutes a replicable resource for future mobility research in similar contexts.

In this article, the Wolf Search algorithm was adapted to solve the problem a single machine with sequence-dependent setup times. To represent the solution of the problem, a permuted discrete coding scheme was proposed. The performance of the algorithm was compared with the Metaheuristic Viral System and Simulated Annealing in 35 instances with sizes between 15 and 150 jobs. From a Variance Analysis, it was found that the Wolf Search and Viral System algorithms are similar in their performance in terms of response quality, however, the Wolf Search algorithm has a low computational time compared to the Viral System algorithm. It is concluded that the Wolf Search algorithm can be used with great certainty to address the problem of production programming on a single machine with sequence-dependent enlistment times, for which it is proposed that it be used in other programming problems of combinatorial production or optimization.

Near-infrared (NIR) imaging plays a crucial role in precision agriculture; however, the high cost of multispectral sensors limits its widespread adoption. In this study, we generate synthetic NIR images (2592 × 1944 pixels) of pineapple crops from standard RGB drone imagery using the Pix2PixHD framework. The model was trained for 580 epochs, saving the first model after epoch 1 and then every 10 epochs thereafter. While models trained beyond epoch 460 achieved marginally higher metrics, they introduced visible artifacts. Model 410 was identified as the most effective, offering consistent quantitative performance while producing artifact-free results. Evaluation of Model 410 across 229 test images showed a mean SSIM of 0.6873, PSNR of 29.92, RMSE of 8.146, and PCC of 0.6565, indicating moderate to high structural similarity and reliable spectral accuracy of the synthetic NIR data. The proposed approach demonstrates that reliable NIR information can be obtained without expensive multispectral equipment, reducing costs and enhancing accessibility for farmers. By enabling advanced tasks such as vegetation segmentation and crop health monitoring, this work highlights the potential of deep learning–based image translation to support sustainable and data-driven agricultural practices. Future directions include extending the method to other crops, environmental conditions and real-time drone monitoring.

Introducción: El problema Job Shop Con Operadores Calificados o Job Shop With Skilled Operators (JSSO) es una extensión del problema clásico Job Shop en el cual, una operación debe ser ejecutada por un conjunto limitados de trabajadores, con el objetivo de minimizar el tiempo de terminación total de los trabajos o Makespan, situación que puede representar distintas aplicaciones en la vida cotidiana. Es un problema complejo y es catalogado como NP-HARD. Objetivo: En este artículo, se aborda el problema JSSO desde la adaptación de un algoritmo conocido como Squirrel Search Algorithm (SSA). Metodología: Se propone un esquema de codificación discreto para el algoritmo SSA utilizando el método Smallest Position Value (SPV). Además, para evitar soluciones que violen las relaciones de precedencia; se corrigen con el método Valid Particle Generator (VPG), el cual garantiza soluciones factibles. Dos versiones del algoritmo se colocan a prueba en 28 instancias propuesta en la literatura para validar su rendimiento. Resultados: Los experimentos computacionales realizados muestran que los dos algoritmos propuestos alcanzan soluciones óptimas en 25 de las 28 instancias analizadas. Además, para las instancias en donde no se logró soluciones óptimas, el gap promedio no supera el 2% para ambas versiones de los algoritmos propuestos. Conclusiones: El esquema de codificación propuesto garantiza la discretización del algoritmo, generando soluciones que convergen hacia el óptimo. Además, la codificación propuesta, permite utilizar de manera natural los operadores de movimiento propuestos originalmente para el algoritmo utilizado. El rendimiento obtenido por los algoritmos es adecuado y de alta calidad.