Recent advances in the telecommunication industry offer great opportunities to citizens and organizations in a globally connected world, but they also arise a vast number of complex challenges that decision makers must face. Some of these challenges can be modeled as combinatorial optimization problems (COPs). Frequently, these COPs are large-size, NP-hard, and must be solved in “real time,” which makes necessary the use of metaheuristics. The first goal of this paper is to provide a review on how metaheuristics have been used so far to deal with COPs associated with telecommunication systems, detecting the main trends and challenges. Particularly, the analysis focuses on the network design, routing, and allocation problems. In addition, due to the nature of these challenges, the paper discusses how the hybridization of metaheuristics with methodologies such as simulation and machine learning can be employed to extend the capabilities of metaheuristics when solving stochastic and dynamic COPs in the telecommunication industry.

Planning and scheduling of testing activities play an important role for any independent test team that performs tests for different software systems, developed by different development teams. This work studies the application of machine learning tools and variable selection tools to solve the problem of estimating the execution effort of functional tests. An analysis of the test execution process is developed and experiments are performed on two real databases. The main contributions of this paper are the approach of selecting the significant variables for database synthesis and the use of an artificial neural network trained with an asymmetric cost function.

This work addresses the problem of using Unmanned Aerial Vehicles (UAV) to deploy a wireless aerial relay communications infrastructure for stations scattered on the ground. In our problem, every station in the network must be assigned to a single UAV, which is responsible for handling all data transfer on behalf of the stations that are assigned to it. Consequently, the placement of UAVs is key to achieving both network coverage and the maximization of the aggregate link capacities between UAVs and stations, and among the UAVs themselves. Because the complexity of this problem increases significantly with the number of stations to cover, for a given fixed number p of available UAVs, we model it as a single allocation p-hub median optimization problem, and we propose a hybrid metaheuristic algorithm to solve it. A series of numerical experiments illustrate the efficiency of the proposed algorithm against traditional optimization tools, which achieves high-quality results in very short time intervals, thus making it an attractive solution for real-world application scenarios.

The problem of independent component analysis (ICA) was firstly formulated and studied in the context of real-valued signals and mixing models, but, recently, an extension of this original formulation was proposed to deal with the problem within the framework of finite fields. In this work, we propose a strategy to deal with ICA over these fields that presents two novel features: (i) it is based on the use of a cost function built directly from an estimate of the mutual information and (ii) it employs an artificial immune system to perform the search for efficient separating matrices, in contrast with the existing techniques, which are based on search schemes of an exhaustive character. The new proposal is subject to a comparative analysis based on different simulation scenarios and the work is concluded by an analysis of perspectives of practical application to digital and genomic data mining.

O fenômeno das notícias falsas é motivo notório de preocupação, devido aos potenciais malefícios que estas causam na vida em sociedade. A classificação automática de notícias falsas (fake news) é um problema que vem sendo abordado no contexto do aprendizado de máquina há certo tempo, mas, mesmo assim, ainda não há tantos trabalhos a respeito realizados na língua portuguesa. Em paralelo, desenvolveu-se a partir dos anos 2020 o emprego de modelos Transformer com dados textuais e, neste contexto, há o modelo BERT (Bidirectional Encoders Representations for Transformers) e a sua variante que foi especificamente pré-treinada para tarefas em língua portuguesa: o BERTimbau. Este trabalho, daí, propõe treinar os dois modelos supracitados, juntos à variante multilingual do BERT, mBERT, na tarefa de classificação de notícias falsas, a partir de diversos conjuntos de dados propostos na literatura, com o objetivo de verificar os potenciais ganhos do emprego de um modelo de linguagem especificamente treinado para o Português. Os resultados obtidos indicam uma superioridade do BERTimbau sobre o BERT e sobre o mBERT na referida tarefa, com uma melhoria média de 2,37% e 1,07%, respectivamente, para os valores de F1-score.