https://ri.ufs.br/jspui/handle/riufs/2491 Thu, 30 Apr 2026 19:34:31 GMT 2026-04-30T19:34:31Z http://ri.ufs.br:80/retrieve/07465a4b-d559-4270-b013-e28e4e81d760/procc.jfif https://ri.ufs.br/jspui/handle/riufs/2491 https://ri.ufs.br/jspui/handle/riufs/24793 Título: Convergência de agile e design: um framework integrativo para eficiência, inovação e melhorias contínuas na experiência do usuário Autor(es): Dantas, Silvio Mario Felix Abstract: Agile is a software development framework that focuses on putting the customer first, prioritizing functional projects over comprehensive documentation, valuing active customer participation, and incorporating feedback through incremental deliveries. The goal is to provide a good user experience. However, research points to shortcomings in problem understanding and solution-finding in projects that adopt Agile. Therefore, its application in conjunction with other approaches is recommended to address these deficiencies. In this context, considering design management approaches as complementary methodologies can generate a valuable combination, integrating design, innovation, and technology. This research aims to create a framework model that integrates characteristics of Design Thinking and User-Centered Design, seeking to enhance the agile SCRUM development process. To this end, literature reviews were conducted on the proposed themes, as well as a systematic literature mapping to build the state of the art. A survey was also conducted with leaders, managers, and developers involved in agile development, in addition to analyzing the points of convergence between design management practices and Agile, forming the necessary basis for the conceptual design of the framework. Based on the findings, a data triangulation is proposed to obtain meaningful insights for the development model. Multidisciplinary frameworks provide a broader perspective for problem-solving; the adoption of such practices represents a significant advancement in the creation of software and products with strategic differentiation and a focus on solving feasible user problems. Mon, 28 Jul 2025 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/24793 2025-07-28T00:00:00Z https://ri.ufs.br/jspui/handle/riufs/24792 Título: Guidelines para adoção do Event Storming com foco em arquitetura de microsserviços Autor(es): Santos, Marcos Cesar Barbosa dos Abstract: Context: Agile development teams require well-defined requirements to maintain productivity. Event Storming serves as a dynamic technique for producing this type of visual documentation with low formalism and compatible with the microservices architecture. Problem: As it is a relatively recent technique with few rules when compared to more established documentation, such as UML, both agile teams and managers may show resistance in using Event Storming. Solution: As a proof of effectiveness, the construction of guidelines for the adoption of Event Storming during the requirements phase will facilitate both the conduct of the technique by new development teams and will increase the reliability of the entire approach, potentially reducing the resistance faced by development and management teams. Method: With the aim of building knowledge from the design of experimental and evolutionary artifacts, this research is based on the methodology of Design Science Research. Thu, 28 Aug 2025 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/24792 2025-08-28T00:00:00Z https://ri.ufs.br/jspui/handle/riufs/24791 Título: A novel approach to use Multi-Armed Bandit for feature selection Autor(es): Monteiro, Keomas da Silva Abstract: This work explores the application of Multi-Armed Bandit (MAB) algorithms for feature selection (FS) in machine learning, aiming to address the challenges posed by high-dimensional data, such as computational complexity and overfitting. While traditional FS methods are widely used, the integration of MAB in this context remains unexplored. This research proposes novel MAB-based algorithms, specifically adapting the Epsilon-greedy (MAB-EgreedyFS) and Upper Confidence Bound (MAB-UCBFS) algorithms, to dynamically manage feature inclusion and exclusion. In this way, the feature set is formed with the aim of providing the best accuracy for the classifier in the classification task. For this, each feature’s status is treated as an "arm" in the bandit problem approach that abstracts the search for the best features as the exploration-exploitation dilemma. During the process a Support Vector Machine (SVM) is applied as the classifier to evaluate the methods. A experimental set was performed, the proposed methods were evaluated in seven dataset and compared against established FS methods: SVM-RFE, extra-trees-based method, genetic algorithm-based method a ANOVA filter method. The results indicate that MAB-UCBFS consistently achieved strong performance, notably ranking as the "Best Method" for most of the evaluated data sets. While not universally superior, MAB-UCBFS demonstrated robust and competitive performance across most scenarios. Statistical analysis using Conover test heatmaps further corroborated these findings, highlighting significant differences between MAB-UCBFS and other techniques on several datasets. This study successfully validates the viability and strong performance of MAB-based algorithms, particularly MAB-UCBFS, as innovative and effective solutions for feature selection. Fri, 29 Aug 2025 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/24791 2025-08-29T00:00:00Z https://ri.ufs.br/jspui/handle/riufs/24781 Título: Análise exploratória e prática da aplicação de NER em notícias sobre saúde Autor(es): Almeida, Samuel Santana de Abstract: Context: Context: The public sector, specifically regarding audits within the Ministry of Health and the Unified Health System (SUS), faces operational bottlenecks due to manual data analysis processes. This inefficiency leads to delays and high costs, hindering the fight against corruption and the assurance of the universal right to health. Objectives: This study aimed to characterize the state-of-the-art in Named Entity Recognition (NER) architectures applied to healthcare and identify the most effective approach for entity extraction and text classification in health news. The focus is on optimizing SUS auditing by comparing the performance of BERT, BERT-CRF, and ModBERTBr models. Methodology: The research employed a Systematic Literature Mapping (SLM), analyzing 310 studies from an initial pool of 5,863, followed by a controlled experiment. The experiment utilized a Natural Language Processing (NLP) pipeline applied to a corpus of 800 health news articles for the training and evaluation of NER and classification tasks. Results: The SLM revealed the dominance of Transformer-based Deep Learning models, with BERT being the most frequent technique (215 studies). In the practical NER experiment, BERT-CRF excelled with the highest recall (0.880), precision (0.855), and F1-score (0.860), while BERT achieved the highest accuracy (0.900). In the classification task, BERT outperformed ModBERTBr across all metrics. Regarding efficiency, BERT was superior in execution time for NER (8min 10s), whereas BERT-CRF was faster in classification (7min 10s). Conclusion: Model effectiveness is task-dependent: BERT-CRF is superior for precise detection in complex sequences (such as audit reports), while BERT is better suited for the rapid screening of large document volumes. It is concluded that the implementation of a hybrid system has high potential to optimize the selection of auditable content in SUS, strengthening integrity and investigation within public processes. Wed, 28 Jan 2026 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/24781 2026-01-28T00:00:00Z