Brazil presents a distinctive convergence of continental-scale climatic diversity, extensive urbanization, large-scale biomass burning, rapid land-use change, persistent air-quality monitoring gaps, and deep social inequalities, producing highly heterogeneous and compound environmental health risks. In this context, treating air pollution and climate change as parallel environmental crises obscures their structural interconnections through shared emission sources, mutually reinforcing exposure pathways, and overlapping health and social consequences. In this narrative review, we critically synthesize scientific and institutional lines of evidence and argue that air pollution and climate risks can be more effectively addressed in Brazil through a single strategic agenda for science, public health, and governance. We first discuss why these challenges cannot be managed in isolation, emphasizing the effects of heat, drought, stagnation events, biomass burning, and extreme weather on pollutant formation, dispersion, and health burden. We then examine Brazil as a critical case where recent regulatory advances coexist with structural limitations in monitoring, data integration, and territorial coverage. Based on this diagnosis, we propose an integrated national agenda organized around five mutually reinforcing priorities: monitoring through hybrid networks; predictive science through climate-informed modeling and early warning; public health through the convergence of epidemiology, toxicology, and mechanistic research; equity-oriented research and action through the explicit incorporation of vulnerability, inequality, and climate justice; and policy appraisal through the assessment of disease burden, economic costs, mitigation co-benefits, and trade-offs. We further discuss the governance mechanisms needed to connect these priorities and translate evidence into coordinated action and adaptive public policies. We also argue that the Amazon should be approached not as an isolated ecological exception but as a central component of a broader Brazilian and Global South discussion on environmental health, land-use change, and climate justice. In this scenario, Brazil has the scientific capacity and regulatory momentum to become a reference in the integrated management of air pollution and climate risks, but this will depend on replacing fragmented approaches with a coordinated framework capable of linking exposure, mechanism, burden, inequality, and action.

This paper presents the identification of emotions using Watson, a natural language processing tool, applied to multi-agent systems. In this approach, Watson acts as an intermediary between agents and identifies the emotions expressed in exchanged messages to assist in the agents’ decision-making. The identification of emotions was based on the OCC model using tokens – words related to each emotion – which are useful for identifying and indicating the intensity of emotions. We built a prototype using the Jason platform to test communication between two agents, with Watson acting as an intermediary to identify emotions based on the OCC model. As an experiment, we present a study in Prisoner’s Dilemma and how emotions change agents’ decision-making.

This paper presents a systematic review on knowledge transfer in multi-agent systems using reinforcement learning. The review followed the PRISMA protocol, analyzing relevant articles from the IEEE Xplore, Scopus, and Web of Science databases. It highlighted research focused on multi-agent reinforcement learning, with works aiming to develop generic algorithms or frameworks for knowledge transfer. Recent approaches enhance agents’ efficiency and adaptability, reducing learning time. However, challenges related to communication robustness and knowledge representations’ compatibility persist.

Given that climate change can exacerbate the health impacts of air pollutants, we evaluated the impact of temperature increase scenarios on air pollutant levels (O3, PM2.5, and PM10) in Porto Alegre and Recife, Brazil. Air pollutants and meteorological data were collected, and simulations were performed using a Support Vector Machine model with radial basis function kernel, applying temperature increases of 0.5°C, 1.0°C, 1.5°C, and 2.0°C to predict future pollutant concentrations. The data were analyzed seasonally and annually. Pearson correlation and principal component analyses (PCA) explored the relation with meteorological conditions. Simulations revealed that rising temperatures do not uniformly lead to increased pollutant concentrations; instead, the effects are highly dependent on local meteorological and climatic conditions. In Porto Alegre, O3 levels increased throughout the year, with a peak of 14.14% during the summer in the + 2.0°C scenario, while PM2.5 and PM10 also showed marked seasonal increases. Conversely, in Recife, O3 levels decreased in some seasons but increased during autumn, with particulate matter levels also rising during the summer. The findings underscore the need for health systems to consider these dynamics in their management strategies through location-specific investigations and emphasize the importance of policy-driven adaptive measures to build climate-resilient health systems.

(1) Background: This study investigated seasonal variations in particulate matter (PM) ratios (PM1/PM2.5, PM2.5/PM10, and PM1/PM10) and their relationship with the meteorological conditions in Rio Grande, Brazil. (2) Methods: PM1, PM2.5, and PM10 levels were collected using low-cost Gaia Air Quality Monitors, which measured PM concentrations at high temporal resolution. Meteorological variables, including atmospheric pressure, temperature, relative humidity, wind speed, and precipitation, were obtained from the National Institute of Meteorology (INMET). The data were analyzed through multiple linear regression to assess the influence of meteorological factors on PM ratios. (3) Results: The results show that the highest PM ratios occurred in winter, indicating a predominance of fine and ultrafine particles, while the lowest ratios were observed in spring and summer. Multiple linear regression analysis identified atmospheric pressure, wind speed, and maximum temperature as the key drivers of PM distribution. (4) Conclusions: This study highlights the importance of continuous monitoring of PM ratios, particularly PM1, which remains underexplored in Brazil. The findings underscore the need for targeted air quality policies emphasizing seasonal mitigation strategies and improved pollution control to minimize the health risks associated with fine and ultrafine PM exposure.

This study developed a predictive model of hospital admissions due to respiratory diseases using environmental and meteorological data from São Paulo (2017-2022). It analyzed hospitalizations classified under ICD-10 codes J00-J99. Weekly public data on air pollutants (PM2.5, PM10, O3, NO2, SO2, CO) and climate variables (temperature, humidity, precipitation, among others) were used. The methodology included feature engineering (lags, moving averages, interactions, trend, seasonality), Lasso regression for variable selection, and application of the CatBoost algorithm optimized via GridSearchCV. The model showed strong performance (R²≈0.895), with good accuracy in estimating healthcare demand. The Shapley Additive Explanations (SHAP) technique ensured model explainability, identifying the most influential predictors of respiratory admissions. The results highlight the potential of AI as a strategic Digital Health tool, especially for early outbreak detection and resource allocation within Brazil's Unified Health System (SUS).

Autonomy in software, a system’s ability to make decisions and take actions independently without human intervention, is a fundamental characteristic of multi-agent systems. Testing, a crucial phase of software validation, is particularly challenging in multi-agent systems due to its complexity, as the interaction between autonomous agents can result in emergent behaviors and collective intelligence, leading to system properties not found in individual agents. A multi-agent system operates on at least three main dimensions: the individual level, the social level, and the communication interfaces. An organizational model formally defines a multi-agent system’s structure, roles, relationships, and interactions. It represents the social layer, capturing agents’ collective dynamics and dependencies, facilitating coherent and efficient collaboration to achieve individual and collective goals. During the literature review, a gap was identified when testing the social layer of multi-agent systems. This paper presents a testing approach by formally introducing steps to map an organizational model, here ℳ oise ^+ , into a colored Petri net. This mapping aims to generate a formal system model, which is used to generate and count test cases based on a coverage criterion. Finally, a use case called Inspector was presented to demonstrate the method by generating test cases, executing the test, and identifying execution errors.

Este artigo apresenta uma revisão sistemática da literatura que tem como objetivo analisar a transferência de conhecimento em sistemas multiagente, com foco particular no nível organizacional. Seguindo o protocolo PRISMA, a revisão examinou publicações de 2019 a 2025 em quatro bases de dados principais: IEEE Xplore, Scopus, Web of Science e ACM Digital Library. Por meio de um processo de seleção estruturado, foram identificados três estudos relevantes, cada um abordando diferentes modelos organizacionais, tipos de conhecimento e estratégias. Os resultados revelam que a literatura científica sobre esse tema ainda é limitada, com a maioria das contribuições centradas em estruturas teóricas e simulações. Foi identificada uma lacuna significativa na forma de ausência de validação empírica. A análise destaca a necessidade de pesquisas futuras que não apenas ampliem o panorama teórico, mas também integrem dimensões sociais, tecnológicas e organizacionais, a fim de promover o desenvolvimento de sistemas multiagente mais eficientes e colaborativos.

This study addresses the rise in respiratory disease hospitalizations associated with air pollution in large urban centers, using São Paulo, 2017 to 2022, as a case study. The objective was to clearly and practically assess the ability of XGBoost to predict daily fluctuations in hospitalizations and to provide operational inputs for public management. We employed a reproducible pipeline with median imputation, stabilization via PowerTransformer, a chronological train and test split at 70 to 30, and hyperparameter tuning with GridSearchCV using TimeSeriesSplit. Interpretability was ensured with SHAP and diagnostics through a correlation matrix. On the test data, the model showed stable performance, R² ≈ 0.65, MAE ≈ 18, RMSE ≈ 22.7, r ≈ 0.81, with errors concentrated around zero. Explanations indicated a dominant contribution of seasonal and temporal markers, month, day of year, and day of week, followed by PM₁₀, PM₂.₅, and NO₂, and the strong correlation between PM₁₀ and PM₂.₅, r = 0.96, confirms redundancy among predictors. We conclude that XGBoost meets the proposed goal by bringing environmental surveillance closer to care management in the Brazilian Unified Health System, SUS, while preserving transparency and practical usefulness. Limitations are acknowledged, and advances are suggested in contextual variables, tail-sensitive loss functions, and benchmarking across algorithms.

A demanda por sistemas com inteligência artificial, como sistemas multiagente, está continuamente crescendo. Ao mesmo tempo, há uma necessidade de desenvolvimento de ferramentas para auxiliar nesta área, garantindo uma melhor tolerância a falhas para o projeto, uma vez que esses sistemas possuem características que tornam o sistema não determinístico e aumentam a dificuldade na realização de testes. Para tentar resolver esse problema, foi desenvolvida uma ferramenta de mapeamento que gera automaticamente um modelo gráfico que pode ser utilizado para identificar caminhos de teste para um determinado sistema multiagente. Esta ferramenta utiliza como entrada um arquivo XML do Moise+, um modelo organizacional para sistemas multiagente, mapeando-o em uma rede de Petri colorida, uma ferramenta de modelagem gráfica e matemática. O mapeamento resultante é utilizado para gerar casos de teste, necessários para validar o modelo Moise+, sendo utilizado como guia durante a realização dos testes do sistema. A automação torna o processo mais rápido e elimina a possibilidade de erro humano.

Educational institutions have been adopting business simulation games as a resource for developing skills and competencies. However, the real-time study of aspects related to learning during their use still needs to further investigation. This work aims to present contributions of a new methodology that considers the analysis of the player’s experience from the physiological, behavioural, and psychological perspectives, supported by biometric devices. Its validation was based on data collection conducted at a university in Brazil, with ten participants during a game monitored by Electroencephalogram and Eye Tracking technologies, relating the behaviour of the cerebral cortex with areas of greater interest and gaze fixation of the players. Additionally, pre-and post-test questionnaires highlighted personal behaviours and collective patterns influenced by aspects such as tutorial and game design elements, prior knowledge, ergonomic issues, cognitive strategy definition, organization of executive functions, and memory formation. The results show that the proposed model can be beneficial in assessing the potential of this type of organizational environment simulation, both for those who use it in the teaching process and for serious game developers.

Knowledge transfer enables the development of complex multi-agent systems featuring agents that share knowledge to execute tasks. Environments shaped by knowledge transfer involve agents assuming specific roles, reasoning about the environment and other agents, and forming organizations that transfer knowledge through well-defined plans and strategies. This paper presents an organizational model for knowledge transfer, introducing a centralizing role, named organizer, responsible for managing relations between the system, agents, and their roles. An interaction protocol is established to guide the step-by-step communication between the organizer and other agents in the system during knowledge transfer. To model knowledge transfer within agent organizations, we employ a dynamic implementation of the Moise+ organizational model, called MoiseLight, enabling the creation of organizations at runtime. We validate the proposal by adapting the model to MoiseLight, demonstrating the organizer's ability to facilitate knowledge transfer among agents following the specified interaction protocol.

The demand for systems with artificial intelligence, such as multi-agent systems, is continuously growing. At the same time, there is a need for the development of tools for helping this area, ensuring better fault tolerance for the project, since these systems have characteristics that make the system non-deterministic and increase the difficulty in carrying out tests. To try to solve this problem, a mapping tool was developed that automatically generates a graphical model that can be used to identify test paths for a given multi-agent system. This tool takes as input an XML file from Moise(+), an organizational model for multi-agent systems, mapping it into a colored Petri net, a graphical and mathematical modeling tool. The resulting mapping is used to generate test cases, necessary for validating the Moise(+) model, being used as a guide when carrying out system tests. Automation makes the process faster and eliminates the possibility of human error.

The demand for systems incorporating artificial intelligence, such as multi-agent systems, is continually increasing. Simultaneously, there is a growing need for developing tools to support this field, ensuring better fault tolerance within projects. This is particularly crucial given that these systems possess characteristics that render them non-deterministic, thereby amplifying the challenge of conducting tests. To address this challenge, a mapping tool has been developed. This tool automatically generates a graphical model, facilitating the identification of test paths for a given multi-agent system. It operates by taking an XML file from Moise+, an organizational model for multi-agent systems, and translates it into a colored Petri net. The resulting mapping serves as a foundation for generating test cases essential for validating the Moise+ model, guiding system testing. Automation streamlines the process, enhancing speed, and eliminating the potential for human error.

Emotion recognition is an increasingly relevant field due to its direct implications for various sectors of society. The area aims to enhance the understanding of how emotions influence human behavior. Exploring brain activity analysis through electroencephalogram signals becomes possible when considering that emotions can manifest non-verbally. In this scenario, machine learning applications prove promising due to the complexity of recognizing emotions from electrical signal data from the brain. The case study focuses on DEAP, a recognized dataset constructed through experiments in electroencephalography, exposing subjects to musical and visual stimuli. The main objective of this work is to present a pipeline for the classification of emotions based on images of topographic maps generated from the EEGLAB tool and electroencephalogram signals. Additionally, the contributions of this work include the presentation of a structured dataset created through the mapping of temporal, spatial, and frequency data derived from topographic images and models for predicting dimensional emotions of arousal and valence based on the new dataset. Results demonstrate accuracies of 85.46% and 85.05% for the classification of low/high arousal and valence emotions, respectively.

The demand for systems with artificial intelligence, such as multi-agent systems, is continuously growing. At the same time, there is a need for the development of tools for helping this area, ensuring better fault tolerance for the project, since these systems have characteristics that make the system non-deterministic and increase the difficulty in carrying out tests. To try to solve this problem, a mapping tool was developed that automatically generates a graphical model that can be used to identify test paths for a given multi-agent system. This tool takes as input an XML file from ℳ oise ^+ , an organizational model for multi-agent systems, mapping it into a colored Petri net, a graphical and mathematical modeling tool. The resulting mapping is used to generate test cases, necessary for validating the ℳ oise ^+ model, being used as a guide when carrying out system tests. Automation makes the process faster and eliminates the possibility of human error.

Este estudo apresenta uma análise das estratégias utilizadas pelos jogadores de um RPG (Role-Playing Game) no contexto de recursos hídricos. Os RPGs são amplamente utilizados em várias áreas porque os indivíduos têm estratégias que se aproximam da realidade. No contexto da Educação Ambiental, o RPG ajuda no processo de compreensão do problema e como cada jogador pensa, analisa e observa uma situação de sua perspectiva e, assim, pode elaborar estratégias que considera relevantes para seu papel no jogo. A principal contribuição deste trabalho é um estudo empírico e qualitativo sobre a motivação dos indivíduos e como eles elaboraram suas estratégias. Como resultados, apresentamos a análise dos hábitos dos jogadores por meio de uma entrevista semiestruturada, a qual resultou em um conjunto de discursos, baseados na técnica do Discurso do Sujeito Coletivo (DSC). Assim, podemos concluir que os jogos, principalmente o RPG, pode ser uma ferramenta de auxílio no processo de aprendizagem ao permitir que situações do mundo real sejam experienciadas.

In Brazil, one of the conditions for issuing the installation license for a hydroelectric plant is the Basic Environmental Project (PBA), which is a document that outlines the management programs for socio-environmental issues, which aim to minimize or mitigate the negative impacts and maximize the positive impacts foreseen with the implementation of the project. Therefore, the relevance of carrying out an evaluation of the potential performance of the programs proposed in the PBA is highlighted, in order to verify if they are in line with the expectations of the environmental agency for projects of this class. This study proposed a Multi-criteria Decision Aid Methodology (MCDA) model to develop and test a potential performance assessment tool that supports licensing bodies in decision-making as to whether or not to approve PBA, based on criteria that define what is relevant from the point of view of licensing bodies.