Fifth-generation technology represents a transformative shift in telecommunications, offering enhanced speed, reliability, and ultralow latency. This paper addresses the challenge of load balancing in 5G networks, especially within multi-access edge computing architectures, by evaluating strategies that ensure quality of service and meet the stringent ultra-reliable low-latency communication requirements.Using Free5GC to emulate 5G core and UERANSIM to simulate user equipment and radio access network behavior, the proposed EdgeLB framework integrates the LoxiLB load balancer to evaluate algorithms such as Round Robin, Weighted Round Robin, Hash-based, and Least Connections. Through Netperf-based experiments, we assessed performance under varying numbers of concurrent connections and UEs, as well as network delays that emulate geographic distance.The results demonstrate that intelligent traffic distribution significantly improves network performance and scalability. All algorithms maintained submillisecond latency in ultra-reliable low-latency scenarios, and some exhibited strong jitter and throughput control. Furthermore, polynomial regression models were derived to approximate the degradation of performance under scaling conditions. These findings validate the EdgeLB architecture as a viable solution for latency-sensitive multi-access edge computing and AI inference applications in 5G environments.

The provisioning of Quality of Service (QoS) in 5G networks plays a crucial role in ensuring efficient performance in scenarios characterized by high demand and dynamism. In the data era, where the generation and consumption of information are growing exponentially, effective traffic management becomes indispensable. This study investigates the application of queueing methodologies — FIFO, PQ, and WFQ — in the context of SDN (Software-Defined Networking) for 5G networks, utilizing ONOS as the SDN controller. The research highlights the importance of traffic management in meeting the stringent requirements of 5G networks, such as ultra-low latency, high reliability, and broad transmission capacity, which are essential for applications like eMBB, URLLC, and mMTC. In addition to a comprehensive theoretical review of 5G, SDN, QoS, and queueing techniques, the study included a practical implementation in a simulated environment using the ONOS software, validating theoretical concepts through a comparative analysis of the impact of queueing on critical metrics such as latency, throughput, packet loss, and jitter. The results demonstrate that optimized queueing techniques are essential for efficient traffic management, reducing latency and increasing throughput across different network scenarios. Thus, this study reaffirms the relevance of integrating SDN and queueing techniques as adaptive and effective solutions for managing modern mobile networks. Furthermore, it highlights promising avenues for future research, including the use of adaptive algorithms in next-generation networks.

This systematic literature review investigates the state of the art in the application of artificial intelligence (AI), particularly convolutional neural networks (CNNs), in the diagnosis of pneumoconioses and asbestos-related diseases (ARDs). A total of 30 articles published between 2020 and 2025 were analyzed, selected from major scientific databases (IEEE Xplore, ScienceDirect, Springer Link, ACM Digital Library, Nature, Wiley Online Library). The analysis addressed the models used types of radiological images (chest X-rays and computed tomography), performance metrics, and limitations. A significant advancement was observed in the use of CNNs and 3D architectures, with an emphasis on automated screening and the interpretability of clinical patterns.

Publications on the Web can influence the public opinion about certain entities (e.g., politicians, institutions). At the same time, a variety of indicators can be extracted from these publications and used to estimate entity performance (e.g., popularity, votes share). This work proposes an automatic method that employs state-of-the-art natural language processing tools to extract indicators about entities mentioned in texts, for estimating the performance of these entities or semantically related ones. Our method calculates performance metrics from performance indicators consolidated for semantically related entities, assess correlations of these consolidated metrics with ground true performance, and uses these metrics to predict certain fluctuations in entity performance. Experimental results in a case study on politics show that consolidated metrics for several interrelated entities are better correlated to observed real performance measures of some target entities and lead to better predictions, than metrics for just one entity.