https://rd.uffs.edu.br/handle/prefix/67 Thu, 28 May 2026 11:23:01 GMT 2026-05-28T11:23:01Z https://rd.uffs.edu.br/handle/prefix/9201 Título: Uma revisão sistemática sobre a aplicação da simulação na representação de sistemas de transportes coletivo urbano Autor(es): Pereira, Maikon Douglas de Souza Primeiro Orientador: Mello, Braulio Adriano de Abstract/Resumen: Computer simulation is a widely used tool in operational research. This approach allows experiments to be conducted on a model that replicates what might occur in reality. Simulation is often used to understand and predict the behavior of systems, such as road traffic systems, bank branches, crowd movement. Among them, problems faced in large cities, such as traffic congestion in public transport systems, can be caused by factors such as overcrowding of vehicles, cost of tickets or number of vehicles in circulation, all of which have a direct impact on the quality of the service offered. the society. In this sense, the planning and control of bus circulation in a city is an important measure for the organization of local traffic. This work presents a systematic literature review on the construction of simulation models that represent the behavior of urban public transport systems. The methodology used in the research was a systematic literature review, in which scientific articles indexed in the Scielo, Google Scholar and CAPES journals portal were selected, using the keywords "simulation", "application" and "urban public transport". The inclusion criteria were the full availability of the article and its publication between the years 2012 and 2022, addressing the research theme. The results indicate that computer simulation has been adopted, in a more expressive way, in studies on urban public transport systems of large proportions and/or complexity. The time and effort to complete the modeling and simulation life cycle in transportation systems act as limiters of their use. Instituição: Universidade Federal da Fronteira Sul Tipo: Monografia Sun, 01 Jan 2023 00:00:00 GMT https://rd.uffs.edu.br/handle/prefix/9201 2023-01-01T00:00:00Z https://rd.uffs.edu.br/handle/prefix/9200 Título: Extração de esquemas em documentos legais não estruturados utilizando LLMs Autor(es): Krzyzaniak, Luan Alecxander Primeiro Orientador: Duarte, Denio Abstract/Resumen: This work explores the use of Large Language Models (LLMs) for schema extraction from unstructured legal documents. The study proposes an approach that integrates data collection techniques, text preprocessing, prompt engineering, and embedding-based evaluation to examine the applicability of LLMs in identifying and organizing legal information efficiently. For evaluation, the Mistral 7B Instruct v0.2 model was applied to 471 Price Registration Records (ARPs), segmented into 2,000-token blocks. Results from the per-document analysis indicate strong performance in data type classification (Type Accuracy: 0.946; Type Precision: 0.972), but moderate semantic performance (Semantic Accuracy: 0.412; Semantic Coverage: 0.714), revealing consistent typing but limitations in semantic correspondence. A second evaluation stage examined a unified JSON constructed from all extracted schemas, in which semantic metrics reached maximum values, showing that the model successfully recovers all expected fields at least once, although with increased noise. The findings suggest that LLMs can serve as auxiliary tools for legal schema extraction, reducing manual effort, but still require additional semantic verification and structural consolidation strategies for practical deployment. Instituição: Universidade Federal da Fronteira Sul Tipo: Monografia Wed, 01 Jan 2025 00:00:00 GMT https://rd.uffs.edu.br/handle/prefix/9200 2025-01-01T00:00:00Z https://rd.uffs.edu.br/handle/prefix/9199 Título: Explorando o uso de LLMs para fuzzing de código Lua Autor(es): Souza, Richard Facin Primeiro Orientador: Feitosa, Samuel da Silva Abstract/Resumen: Fuzzing is a crucial technique for finding vulnerabilities in software, but its effectiveness in scripting languages such as Lua is limited by the difficulty of generating semantically valid test inputs. This work proposes a methodology that uses Large Language Models (LLMs) to generate semantically rich mutations for fuzzing Lua scripts. Our approach involves developing a fuzzer prototype that leverages an LLM’s in-context learning capabilities to create syntactically and semantically plausible code variations. We will validate this methodology by evaluating the code coverage gain of mutations relative to original seeds, the effectiveness in bug identification, and the execution time of the process, aiming to demonstrate the feasibility of using LLMs for the security of systems utilizing Lua. Instituição: Universidade Federal da Fronteira Sul Tipo: Monografia Wed, 01 Jan 2025 00:00:00 GMT https://rd.uffs.edu.br/handle/prefix/9199 2025-01-01T00:00:00Z https://rd.uffs.edu.br/handle/prefix/9198 Título: Validação automática de respostas técnicas automotivas utilizando modelos de linguagem e recuperação de informação Autor(es): Vogt, Rodrigo Ediel Primeiro Orientador: Dal Bianco, Guilherme Abstract/Resumen: Advances in large language models have enabled the automation of complex tasks involving the evalu- ation of technical content. This study investigates the use of Large Language Models to validate the coherence of Question–Answer (QA) pairs extracted from an automotive forum, comparing three approaches: zero-shot classification, retrieval based on semantically similar questions (few-shot), and retrieval based on excerpts from technical manuals. Experimental results indicate a progressive improvement in performance as more structured context is introduced. While the zero-shot approach yields F1-scores below 50%, the use of similar questions as contextual examples provides moderate gains. The best results are achieved with manual-based retrieval, which increases the F1-score to over 70%, highlighting the importance of authoritative technical documentation for reliable automatic answer validation. Instituição: Universidade Federal da Fronteira Sul Tipo: Monografia Wed, 01 Jan 2025 00:00:00 GMT https://rd.uffs.edu.br/handle/prefix/9198 2025-01-01T00:00:00Z