Sistema Regional de Información
en línea para Revistas Científicas de América Latina,
el Caribe, España y Portugal

Fog computing is an emerging paradigm that extends cloud computing by providing computation, communication, and storage services at the network's edge, closer to end devices. This evolution has been driven by the rapid proliferation of Internet of Things (IoT) devices, which generate diverse task requests. Processing these tasks in the cloud can overload its infrastructure and jeopardize the deadlines of time-sensitive requests. To address these challenges, Cisco introduced the con- cept of fog computing in 2012, positioning it as an extension rather than a replace- ment of cloud computing. However, one significant challenge in fog computing is the efficient assignment of tasks to appropriate resources to minimize response time and enhance throughput. In response to this issue, we developed a four-layer model for fog computing based on a systematic literature review. This model incorporates a priority-based task scheduling algorithm designed to optimize task scheduling in terms of response time. Tasks are categorized as simple, medium, or large/complex, with simple and medium tasks assigned to the nearest fog layer based on priority, while large tasks are allocated to the aggregate fog layer. The proposed algorithm was evaluated using a selected simulator, chosen after a systematic review of exist- ing options. In the experiments, we assessed the performance of the proposed algo- rithm using ten different task sets with varying lengths, assigned to different layers of the fog node. A comparative analysis was conducted with the Shortest Job First (SJF) algorithm, which is recognized in the literature as one of the most effective scheduling algorithms. Results indicate that tasks smaller than 4,280 MB should be assigned to the Nearest Fog Node (NFN) for improved performance, while larger tasks are more effectively processed in the Aggregate Fog Node (AFN). Addition- ally, a minimum threshold task size of 50 MB is established, suggesting that smaller tasks may not require specialized scheduling. The findings demonstrate that the pro- posed algorithm significantly reduces the response time of tasks by effectively man- aging the assignment of simple and medium tasks to the nearest fog node and large tasks to the aggregate node, outperforming SJF.

This study investigates the performance of the YOLOv8 object detection algorithm for fuel tank detection using unmanned aerial vehicles (UAVs) under various conditions and perspectives. UAVs, with their agile mobility and ability to capture high-quality images from different angles, are proven to facilitate the detection of fuel tanks, which play a critical role in various industries. The integration of UAVs with YOLOv8 has led to significant advancements in automation and precision in inspection processes within the energy and industrial sectors. YOLOv8, a single-stage deep learning-based object detection model, demonstrates superior architecture compared to previous YOLO iterations, showcasing its strengths in speed and accuracy for object detection tasks. The model achieves a precision of 0.888, recall of 0.896, and mAP of 0.891, confirming its strong capabilities in detecting fuel tanks and supporting the sustainability of industrial and energy operations. With a processing time of 41 ms, YOLOv8 proves to be highly effective for real-time applications. This research highlights the importance of optimizing UAVs and deep learning models for reliable data collection in challenging environments and demonstrates their potential for use in fuel tank monitoring and infrastructure reliability tracking across industries. While accurate detection successes are noted, the study emphasizes the need for further optimization of the algorithm to address false positives and undetected objects in real-world applications. Future work will explore the adaptation of high-performance algorithms such as YOLOv8 for broader object detection scenarios and their testing under diverse environmental conditions.

This study aims to classify the educational innovation of Mexico’s state governments using the ordered weighted averaging (OWA) operator and its extensions. This method generates a ranking of the Mexican federal entities and constructs an educational innovation index. The results indicate that Mexico City has the highest evaluation levels, while Baja California Sur ranks lowest. Applying this technique not only enables these territories to be ranked according to the relative importance of each criterion, but also produces alternative scenarios that underscore the relevance of these elements. Therefore, the information is valuable for policymakers, as it supports the allocation of resources based on areas of opportunity. Finally, the document illustrates the application of the OWA operator and its extensions to classify the educational innovation of Mexico’s state governments.

An optimization model is presented for the efficient energy management in smart grids (SGs) that integrate electricity generation, distribution, and storage in the residential sector. The model's objectives include minimizing the system's total operating costs, reducing users' dependence on the external power grid, and optimizing the use of internally generated energy. This optimization model is proposed for energy management in a SG focused on the residential sector, using renewable energy from photovoltaic panels (PV). This bottom-up engineering modeling approach centers on household consumption behavior. Therefore, factors such as household sociodemographic characteristics, income level, housing attributes and assets, energy expenditure by source, and the type and number of devices were considered.

Object detection is one of the critical and essential tasks in computer vision, with applications ranging from surveillance and industrial control to robotics and image analysis. This research presents a performance analysis of different YOLO (You Only Look Once) versions and a transformer model. The study evaluates YOLOv8, YOLOv9, YOLOv10, YOLOv11, and the RT-DETR (Real-Time Detection Transformer) model for object detection. The experiment uses a dataset of 1,730 images classified into five types: birds, dogs, cats, plants, and fruits, each with its subtypes. Also, we test with a frog dataset of 613 images which are characterized as complex images because present occlusion, complex backgrounds and variations in illumination. In addition, its performance is evaluated using standard metrics such as Precision, Recall, mAP50, and mAP50-95.

This paper explores the application of advanced deep learning models, particularly YOLOv7, for helmet detection in construction sites to enhance workplace safety. The study evaluates YOLOv7's performance through key performance metrics, demonstrating its effectiveness in accurately detecting workers wearing helmets. A comparative analysis with YOLOv8 highlights YOLOv7’s superior performance in detection accuracy and computational efficiency, making it a practical choice for resource-constrained environments. Despite challenges such as adapting to dynamic and complex construction site conditions, YOLOv7 proves to be a reliable and efficient tool in real-time safety monitoring. The findings suggest that YOLOv7-based helmet detection systems can significantly reduce human error, improve worker safety, and contribute to lowering incident rates. Thus, the results emphasize the potential of deep learning in transforming safety protocols, ensuring regulatory compliance, and fostering a culture of accountability in construction.

This study investigates the application of deep learning algorithms, specifically SSD and YOLOv7, for pipeline damage detection using remote sensing technology. The research evaluates the performance of both algorithms in terms of precision, recall, mean average precision (mAP), and F1 score, using a dataset collected through UAV-based imagery. SSD demonstrated superior precision but slightly lower recall, while YOLOv7 excelled in recall and overall detection ability, making it more suitable for comprehensive inspections where missing defects is critical. The findings emphasize the importance of context-specific algorithm selection, with SSD being ideal for real-time monitoring systems and YOLOv7 for applications requiring high recall. Furthermore, the study explores potential improvements to SSD, including transfer learning, data augmentation, and advanced feature extraction techniques, to enhance recall and overall performance. The results offer valuable insights for optimizing pipeline damage detection in varying operational environments.

This paper presents the HICCS algorithm, a novel clustering approach that handles mixed and incomplete data. HICCS improves clustering by using compact sets as initial clusters, employing holotypes to measure intergroup dissimilarity, and merging clusters based on similarity in an order-independent manner. Additionally, it incorporates a user-defined similarity function, making it adaptable to various real-world domains. Furthermore, we introduce the IS-HICCS algorithm for instance selection, which reduces the instance set without compromising classifier accuracy, highlighting clustering's potential to enhance supervised classification models. We evaluate HICCS and IS-HICCS on synthetic and real-life datasets, showing their statistically superior performance compared to other clustering and instance selection methods, respectively

Prompt engineering in the context of operations emerges as a key discipline to optimise artificial intelligence (AI) models for specific operational tasks. Considering the importance of this field, our group offers a current review of designed prompts using language models in business operations. At this stage, the study focuses on confirming the advancement of prompts in response to their precise formulation and applicability in real-world scenarios and different engineering approaches. We use the gold mining problem to evaluate prompt techniques such as Few-shot, Chain-of-thought, and Tree-of-thoughts (ToT) in LLMs. The results show the importance of adapting the prompts to the type of technique and the characteristics of the problem at hand. Our research also offers theoretical and practical foundations for their integration with AI models, highlighting the importance of prompt engineering to enhance automation and decision-making in business environments.