The widespread embrace of the Internet of Things (IoT) and complementary technologies such as Wireless Sensor Networks (WSNs) has significantly driven down the costs associated with IoT devices. Despite this, seamlessly integrating these advancements into the management of sensors in practical settings remains a formidable task. This research endeavors to confront these implementation challenges by introducing an architectural model for an automated monitoring system dedicated to embedded devices, complemented by creating a user-friendly interface. To validate the efficacy of the proposed model, a water quality monitoring system is implemented, utilizing readily available commercial off-the-shelf components.

The quality of public transport is essential when considering urban mobility in large cities. Several factors, such as the increase in urban population, rain, and traffic events, can impact mobility, causing congestion. Addressing this issue is essential for the population and is part of the UN’s 2030 Agenda for Sustainable Development goals. Integrating data from different sources is crucial to understanding and planning urban traffic. This work aims to provide a dataset with spatiotemporal information on the mobility of municipal buses, including the estimated emission of polluting gases and the rainfall volume in Rio de Janeiro from 2014 to 2023. Its format facilitates integration with other Rio de Janeiro City Hall datasets, enabling the increase and deepening of the analyses. This work is the first to combine data from bus observation with positional information on neighborhoods and rainfall regions, rainfall volumes, and pollutant gas emissions. Thus, its availability opens opportunities for research topics involving public transport associated with environmental indicators and data science with time series studies and positional data.

This study addresses the Wireless Sensor Network Planning Problem with Multiple Sources/Destinations (WSNPMSD), an optimization challenge focused on reducing the sensor count within a network topology for a specified area, considering numerous sources and destinations. We introduce a hybrid strategy for tackling WSNP-MSD, particularly effective for large-scale scenarios, combining a Biased Random-key Genetic Algorithm with a Local Branching Technique. This methodology is justified by the limitations exact methods may encounter when the number of variables increases. Through computational experiments, we demonstrate the superiority of our proposed method over conventional exact methods in managing large instances of the WSNP-MSD.

One big concern in soccer professional teams is to search for preventive measures to reduce the frequency of harmful episodes in their athletes since these episodes greatly impact the sports industry and affect both the team’s performance and the association’s economic situation. Thus, the present work proposes a methodology to predict non-contact injury episodes that may affect them in a microcycle through Data-centric AI concepts. The prediction model is trained using a dataset related to professional soccer athletes. The most interesting result were with AUC-ROC of 79,8%. About the performance improvement strategies applied, the best undersampling ratio was 70/30, PCA with one or two principal components did best, and the Decision Tree algorithm excelled.

Autonomous sailboats present unique challenges for Unmanned Surface Vessel (USV) research due to the dynamic nature of maritime environments, where variables like wind direction, ocean currents, and obstacles continuously change. This paper provides a detailed comparison of two advanced trajectory planning methods: Deep Reinforcement Learning (DRL) with Artificial Potential Fields (APF) and A* with Proportional-Integral (PI) control. Both techniques are evaluated using a high-fidelity simulation environment in Gazebo, specifically designed to model realistic maritime conditions, including varying wind speeds and moving obstacles. The performance of each approach is measured in terms of obstacle avoidance, trajectory accuracy, and energy efficiency. Quantitatively, DRL with APF reduced navigation time to 4 minutes and 49 seconds, while A* with PI control required 20 minutes and 10 seconds, achieving success rates of 92% and 75%, respectively. The results demonstrate that DRL with APF not only provides smoother and more adaptive trajectories but also significantly improves energy efficiency, making it a more robust and flexible solution for dynamic and uncertain maritime environments. These findings suggest that DRL with APF holds great potential for applications in autonomous maritime navigation, particularly in scenarios that demand real-time adaptability and efficiency.

Unmanned vehicles keep growing attention as they facilitate innovative commercial and civil applications within the Internet of Things (IoT) realm. In this context, autonomous sailing boats are becoming important marine platforms for performing different tasks, such as surveillance, water, and environmental monitoring. Most of these tasks heavily depend on artificial intelligence (AI) technologies, such as visual navigation and path planning, and comprise the so-called AI of Things (AIoT). In this article, we propose 1) the OpenBoat, an automating system architecture for AIoT-enabled sailboats with application-agnostic autonomous environment monitoring capability and 2) the F-Boat, a fully functional prototype of OpenBoat built with commercial off-the-shelf (COTS) components on a real sailboat. F-Boat includes low-level control strategies for autonomous path following, communication infrastructure for remote operation and cooperation with other systems, edge computing with AI accelerator, modular support for application-specific monitoring systems, and navigation aspects. F-Boat is also designed and built for robustness situations to guarantee its operation under extreme events, such as high temperatures and bad weather, through extended periods of time. We show the results of field experiments running in Guanabara Bay, an important aquatic ecosystem in Brazil, that demonstrate the functionalities of the prototype and demonstrate the AIoT capability of the proposed architecture.

Devido ao aumento do comércio eletrônico e do uso de cartões de crédito, as fraudes com cartões de crédito tornaram-se um grande desafio para as entidades envolvidas. Apesar dos prejuízos, essas fraudes ainda representam uma pequena parte das transações, criando um problema de desbalanceamento de dados nas áreas de detecção de fraudes do sistema financeiro. Este trabalho avalia várias combinações de técnicas de seleção de atributos, balanceamento de classes e algoritmos de classificação. Para balancear as classes, foram usadas técnicas de subamostragem, superamostragem e ajustes de limiares nos classificadores. As combinações foram testadas em dois conjuntos de dados desbalanceados, avaliados pela métrica escore F1. Os resultados mostram um ganho de desempenho quando são implementadas técnicas de balanceamento de dados e otimização de limiares de classificação.

The Bandwidth Minimization Problem for Sparse Matrices is a well-known NP-Hard problem critical in numerous significant scientific applications. The Cuthill-McKee algorithm, a heuristic based on degree centrality for minimizing bandwidth, is a common solution approach. One can integrate other centrality measures into the Cuthill-McKee method or similar algorithms. This work explores the impact of utilizing these diverse centrality measures on the performance of the Cuthil-lMcKee heuristic. It introduces a novel multi-centrality constructive algorithm designed as an alternative for practical applications emphasizing efficient execution for large linear systems. The results demonstrate clear advantages of considering multiple centrality measures over solely degree centrality. This approach notably enhances the heuristic's effectiveness, offering significant improvements in solving complex bandwidth minimization problems.

The widespread adoption in the educational system of information and communications technologies allows the use of interactive simulations, able to support a meaningful insight into the fundamental laws and concepts of electromagnetic theory, which, in a classical approach, would require a vector calculus background and three-dimensional geometrical resourcefulness, typically not maturated by the students in undergraduate engineering programmes. The use of simulation tools based on finite element analysis can facilitate the learning process by allowing users to create and/or exploit visual and more accurate models. ONELAB (Open Numerical Engineering LABoratory) is a simulation platform that integrates several modelling tools, including Gmsh, a three-dimensional mesh modelling software. This simulation tool is able to provide interaction, accuracy, and visual interpretations of classical problems using the fundamental laws of electromagnetism. The application with the basic laws of electromagnetism has been developed to run on mobile devices, besides desktops, to improve its ease of access and dissemination.

SummaryThe breadth‐first search procedure is an algorithm that traverses the vertices of a graph, determining the distance from each vertex to the initial vertex. The distance is infinite for a non‐reachable vertex from the starting vertex. Despite having an efficient serial version, this important algorithm is irregular, making its effective parallel implementation a daunting task. This paper shows the results of an OpenMP‐based implementation of the breadth‐first search procedure using the bag data structure. Furthermore, the code relied on the C++ programming language. This paper reimplements an existing proposal coded using the Cilk++ programming language. The experiments relied on 32 strongly connected graphs and 31 disconnected graphs in executions performed on two machines. The first machine contained 28 cores and two threads per core. The second machine comprised 48 processing cores, with hyperthreading disabled. Regarding the serial version, the parallel implementation yielded a speedup of up to 20× when using 28 processing cores and up to 25× when using 56 threads in tests performed on a machine with the first generation of Intel® Xeon® Scalable processors. Furthermore, the new parallel implementation yielded speedups of up to 45× when using 48 cores in experiments performed on a machine with the second generation of Intel® Xeon® Scalable processors.

Unmanned surface vessels of sailboat type are becoming important platforms for tasks such as surveillance and environmental monitoring. However, making them fully autonomous remains a challenge due to the complexity of their operating environments. In this paper, we propose a unified control architecture for autonomous sailboats that integrates low-level control strategies, such as PID for rudder control and fuzzy logic for sail adjustment. These traditional control techniques are adapted to the sailboat’s dynamics and have been experimentally validated in real-world scenarios. Future work will focus on developing a hierarchical reinforcement control (HRC) system, integrating Artificial Potential Fields (APF) and A* for high-level path planning and obstacle avoidance and Proximal Policy Optimization (PPO) for low-level control.

Os Sistemas de Gerenciamento de Banco de Dados (SGBDs) desempenham um papel primordial em e-Science devido à necessidade de gerenciar e analisar grandes volumes de dados de forma eficiente. MongoDB e PostgreSQL são dois dos SGBDs mais utilizados na atualidade, cada um com suas características únicas que atendem a diferentes necessidades de armazenamento e processamento de dados. Este trabalho apresenta uma análise comparativa entre o MongoDB e o PostgreSQL, avaliando o desempenho e a eficiência de ambos os sistemas ao lidar com consultas complexas e cargas de trabalho de análise de dados. Resultados preliminares indicam que, apesar do MongoDB mostrar eficiência em consultas específicas, o PostgreSQL superou em desempenho na maioria dos testes.

The last few years have been marked by the insertion of renewable technologies in the global energy matrix, such as wind and solar energy, which are considered clean energies with low environmental impact. Wind turbines, responsible for the energy conversion process, are complex equipment that are expensive and susceptible to numerous failures. Monitoring turbine components can help detect failures before they occur, reducing equipment maintenance costs. This work compares the training time of different techniques for tuning hyperparameters in supervised machine-learning models for fault detection in wind turbines. Results show the importance of data optimization during model training.

Com o crescente uso do conceito de IoT e das ferramentas que integram essa tecnologia, como as RSSF (Rede de Sensores Sem Fio), o custo agregado dos dispositivos que a disponibilizam tem caído gradativamente. Todavia, a integração dessa tecnologia no gerenciamento de sensores no campo ainda é um desafio de implementação. Este trabalho apresenta a construção de um modelo de arquitetura, responsável pela implementação de um sistema de monitoramento automatizado de dispositivos embarcados, bem como a construção de uma interface simples para o usuário final. A arquitetura é avaliada por meio da implementação de um sistema de monitoramento de qualidade de água.

Os últimos anos têm sido marcados pela inserção de tecnologias renováveis na matriz energética mundial, como a energia eólica e solar, que são energias limpas e de baixo impacto ambiental. As turbinas eólicas, responsáveis pelo processo de conversão energética, se constituem por equipamentos complexos de alto custo e suscetíveis a inúmeras falhas. O monitoramento dos componentes das turbinas pode auxiliar na detecção de falhas antes que elas ocorram, reduzindo os custos de manutenção do equipamento. Este trabalho compara duas técnicas para determinação de hiperparâmetros de modelos centrados em dados na detecção de falhas em turbinas eólicas. Resultados mostram a importância da seleção e otimização de dados para o problema.

In cognitive wireless networks, opportunistic network devices can be programmed to take advantage of licence holders' idle times and dynamically adjust their operating parameters to improve transmissions. For this to be successful, these idle periods must be reliably detected. To support this requirement, this work proposes a cooperative detection mechanism for the signals transmitted by the licenced system through the use of positioning-enabled devices. Such devices can provide information to guide and control opportunistic network devices to limit interference to the licenced system. Simulations show that keeping interference within specification limits makes it possible to maintain opportunistic network communications in an ad hoc scenario with quality.

We introduce a study about the possibility of using currently developed sailboat robots as tools for motivating learning skills by undergraduate students, including programming abilities, among other disciplines. By way of a survey done with several (former) undergraduate students that worked on autonomous sailboat projects in two different institutions, we demonstrate that it can be an interesting learning resource. These students used it both as a final course project or even only as project participants. Ultimately, we figured out that the platforms can be used as supporting artifacts for Problem-Based Learning in several disciplines. Their use could be restricted due to the space necessary. However, smaller versions have been pointed out as a solution. Another positive point is the motivation that it gives to the students.

The identification of olive-tree cultivars is a lengthy and expensive process, therefore, the proposed work presents a new strategy for identifying different cultivars of olive trees using their leaf and machine learning algorithms. In this initial case, four autochthonous cultivars of the Trás-os-Montes region in Portugal are identified (Cobrançosa, Madural, Negrinha e Verdeal). With the use of this type of algorithm, it is expected to replace the previous techniques, saving time and resources for farmers. Three different machine learning algorithms (Decision Tree, SVM, Random Forest) were also compared and the results show an overall accuracy rate of the best algorithm (Random Forest) of approximately 93%.