Este trabalho apresenta o RingCare, um Sistema de Informação em Saúde baseado em IoHT para monitoramento domiciliar contínuo de idosos. A solução integra um aplicativo Android a vestíveis de baixo custo, permitindo a coleta e consolidação de métricas como frequência cardíaca, saturação de oxigênio e padrões de sono. O sistema adota princípios de computação ubíqua e o ciclo autoadaptativo MAPE-K para analisar dados e gerenciar alertas, incluindo uma etapa de confirmação pelo usuário antes do escalonamento ao cuidador. Testes funcionais em ambiente controlado indicam a viabilidade técnica da arquitetura, demonstrando que a integração de dispositivos comerciais e serviços em nuvem pode viabilizar monitoramento remoto com baixa intrusividade.

Este trabalho apresenta a aplicação de uma abordagem baseada em Software Supply Network (SSN) para a avaliação da saúde e da qualidade de Ecossistemas de Software (ECOS). A abordagem fundamenta-se na modelagem estrutural do ecossistema, possibilitando a análise sistemática de dependências, relacionamentos e indicadores associados à estabilidade, evolução e sustentabilidade. A aplicação foi realizada no ecossistema SIPPA, caracterizado como descontinuado, com o objetivo de examinar sua configuração estrutural e identificar padrões relacionados ao seu processo de declínio. Os resultados revelaram evidências de degradação estrutural, incluindo a redução da conectividade entre atores e concentração de dependências críticas, apontando fragilidades compatíveis com a perda gradual de vitalidade do ecossistema.

A vacinação é fundamental para a prevenção de doenças imunopreveníveis, especialmente em populações vulneráveis. Este trabalho apresenta o SIVEIN, um sistema web para automatizar a análise de dados vacinais do SI-PNI no Polo Base Indígena de Tocantinópolis-TO, substituindo processos manuais. A solução gera indicadores de cobertura e calcula automaticamente o aprazamento de doses infantis, tendo sido validada com profissionais de saúde pelo modelo TAM, com resultados que indicam alta utilidade, facilidade de uso e potencial de adoção para o fortalecimento da vigilância vacinal.

A integração da IoT com as redes 5G amplia o número de dispositivos conectados e a complexidade do tráfego, intensificando desafios de segurança. Técnicas de Aprendizado de Máquina têm sido utilizadas para detectar padrões de ataques em redes. Este artigo apresenta o MARIA, uma solução desenvolvida para identificar e propor medidas de mitigação para ataques direcionados a dispositivos IoT em redes 5G. O Maria é composto por seis módulos e, como parte de seu processo, utiliza algoritmos supervisionados para detecção de ataques, viabilizando respostas rápidas. Uma avaliação do Maria é realizada em um testbed. Os resultados evidenciam a eficácia do MARIA na detecção em tempo real de diferentes tipos de ataques.

Context: Software Ecosystems (SECO) are a set of actors and components that function as a unit, relating to each other based on a common interest in providing solutions or services to the software industry. Problem: For a better visualization and understanding of SECOs, recent studies propose modeling the network formed by them. However, there is still no formalized modeling standard for this area, and there is a lack of tools, approaches, and notations that assist modeling. Solution: In this context, this work aims to present an evolution of the SECO modeling tool, called ECOS Modeling, in its version 4.0. In this version, some new features were added, such as saving the registration and login in the tool, saving and sharing the model in the repository, generating an analysis report of the SECO evolution, viewing the numerical data of the model and making the tool available in other languages. IS Theory: General systems theory, specifically the interfaces between different parts of systems and solutions that communicate, exchanging information. These parts can be systems from different institutions that require integration, consisting of Information Systems. Method: The tool evaluation was planned based on the TAM (Technology Acceptance Model), widely used to measure technology acceptance. The process involved the participation of 49 experts with experience in the areas of software and systems engineering. The selection of experts sought to ensure diversity of profiles, including academics and industry professionals, to broaden the scope and relevance of the results. Summary of Results: The evaluation results demonstrated strong validation of the tool, with experts rating it as highly useful in terms of usability, functionality, and alignment with requirements. The majority (73%) found the tool very useful, 71% stated that it fully met the proposed requirements, and 69% reported ease in finding information and resources. The tool’s navigation was considered clear and easy by 55%, while 49% always knew their location and next steps within the tool. In addition, 55% of experts found the interface visually appealing and 45% reported low mental effort when using it. The study also revealed that 55% used modeling tools frequently and 63% worked with tools saving models in repositories, reinforcing the relevance and suitability of the tool for its target audience. Contributions and Impact in the IS area: As an emerging area, the results contribute to Information Systems by providing a practical tool for modeling, analyzing and evolving SECO. The main contribution is to fill the gap of a formal standard for SECO modeling, allowing the visualization and sharing of ecosystem dynamics, in addition to offering detailed reports that support the understanding of its evolution and identification of deficiencies.

The exponential growth of data and the advancement of computational tools have made Data Science (DS) an essential discipline for addressing complex societal challenges. In the public sector, Evidence-Based Public Policies (EBPP) leverage data-driven insights to enhance governance transparency, efficiency, and effectiveness. However, the integration of Data Science into policymaking presents challenges, including data quality, interdisciplinary collaboration, and institutional resistance. This paper introduces BEPP-DS, a structured methodology for developing EBPP using DS principles, emphasizing transparency, reproducibility, and scalability. The methodology is informed by real-world applications such as Big Data Social and Big Data Fortaleza, which illustrate how data-driven strategies improve policy design, implementation, and monitoring. BEPP-DS defines a structured framework, from problem identification to policy evaluation, ensuring data-driven decision-making in governance. The methodology provides a replicable model for governments seeking to harness Data Science in policy formulation. Future work includes expanding AI-driven analytics and strengthening citizen engagement in data governance.

BACKGROUND: Continuous Quality of Life (QoL) monitoring enables many benefits, such as early healthcare interventions. This work uses Internet of Health Things (IoHT) data and Machine Learning to infer physical and psychological Quality of Life measures. METHODS: We conducted a longitudinal study with 44 participants for six months. Health data were collected daily through smartphones and wearables, and the participants answered the WHOQOL-BREF questionnaire weekly. Then, five Machine Learning models were trained to evaluate their ability to estimate users’ QoL. RESULTS: Random Forest (RF) had the best results considering the Root Mean Squared Error (RMSE). RF got an RMSE of 7.8618 for the physical domain and 7.4591 for the psychological domain. CONCLUSIONS: Overall, it is possible to use IoHT data to infer users’ QoL, considering a certain margin of error; RF had a reasonable performance for this problem and it was not found any decisive feature for the inference process. This last point reinforces that QoL inference using IoHT data is not trivial, and only combining a large number of features can give relevant insights into users’ QoL. Project approved by UFC ethics committee (ID 56153322.0.0000.5054) on March 9, 2022.