Contém os trabalhos de conclusão de curso dos alunos de Ciência de Dados e Inteligência Artificial (Bacharelado) https://repositorio.ufpb.br/jspui/handle/123456789/35370 2026-09-03T14:30:57Z 2026-09-03T14:30:57Z Oliveira, Tales Nobre Leite Dias de https://repositorio.ufpb.br/jspui/handle/123456789/38692 2026-08-19T06:13:33Z 2025-05-12T00:00:00Z

Título: CACTO: Sistema de monitoramento de veículos de carga Autor(es): Oliveira, Tales Nobre Leite Dias de Orientador: Barbosa, Yuri de Almeida Malheiros Abstract: The increasing volume of goods in transit within the state of Paraíba, coupled with the growing sophistication of tax evasion strategies, has driven the need for technological solutions to modernize tax enforcement. In this context, the CACTO System (Online Control and Monitoring of Goods in Transit), developed by the State Treasury Department of Paraíba (SEFAZ-PB) in partnership with the Federal University of Paraíba (UFPB) and the Paraíba Foundation for Education, Technology and Culture (FUNETEC-PB), stands out as a strategic tool for monitoring freight vehicles. The system processes large volumes of data from license plate recognition and electronic tax documents to automatically generate inspection alerts based on business rules. This study aims to analyze CACTO's architecture, operational workflows, and criteria for alert generation and handling, based on official technical documentation and a systematization of its main features. The goal is to demonstrate how this web-based platform applies big data concepts to combat tax evasion and support decision-making. Criteria such as alert coverage, system stability in real-world environments, and the quality of implemented fixes were evaluated. The findings point to improvements in failure traceability and technical reliability, despite the system still being under active development. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-05-12T00:00:00Z Santos, Luiz Fernando Costa dos https://repositorio.ufpb.br/jspui/handle/123456789/38690 2026-08-19T06:13:35Z 2025-05-08T00:00:00Z

Título: PUMLE: A Framework for Data-Driven Applications in Underground Carbon Sequestration Venture Autor(es): Santos, Luiz Fernando Costa dos Orientador: Peixoto, Gustavo Charles de Oliveira Abstract: PUMLE is a framework designed to seamlessly manage large datasets generated from numerical simulations of CO2 injection into underground reservoirs. Using an architecture inspired by the Medallion model, the workflow covers the key stages of the data lifecycle, from generation through batch simulations to the final storage of results in efficient file formats, prioritizing minimal computational effort. PUMLE is intended to generate high quality data to support machine learning experiments aimed at predicting the dynamics of CO2 plumes in future Brazilian carbon sequestration projects, particularly those based on techniques aware of the physical phenomenology behind the injection process. Performance metrics indicate that while the numerical solution accounts for the bulk of processing time, PUMLE’s subsequent data ingestion, transformation, and storage stages demonstrated high efficiency, collectively consuming only about 1.4% of the total wall-clock time in reference simulation tests. This tool is expected to facilitate the creation of consistent datasets, providing scalability and reproducibility for training, testing, and prototyping data-driven solutions focused on the development and monitoring stages of carbon sequestration ventures in heterogeneous domains. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-05-08T00:00:00Z Aguiar, Lucas Miranda de https://repositorio.ufpb.br/jspui/handle/123456789/38688 2026-08-19T06:13:29Z 2025-05-19T00:00:00Z

Título: Uma Abordagem em CNN para Filtragem Rápida de Minúcias em Fingerprints Autor(es): Aguiar, Lucas Miranda de Orientador: Batista, Leonardo Vidal Abstract: Minutiae extraction represents a fundamental process for ensuring reliability in fingerprint recognition systems. This paper introduces an optimi zed hybrid architecture combining adaptive Gabor filtering with an extremely lightweight CNN (125,601 parameters) for robust minutiae validation. Our CNN post-processing stage analyzes 29×29 pixel patches from the initial Gabor iteration, achieving state-of-the-art performance on NIST SD4 with a 1.89% Equal Error Rate- a 30% improvement over conventional approaches. The implementation demonstrates remarkable efficiency, processing each minutia in 1ms through optimized C++ single-thread execution. These advancements prove that carefully designed lightweight neural architectures can significantly enhance biometric systems while meeting real-time operational constraints in embedded environments. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-05-19T00:00:00Z Souza, Jansen Cruz de https://repositorio.ufpb.br/jspui/handle/123456789/38686 2026-08-19T06:13:31Z 2025-05-19T00:00:00Z

Título: Triagem de Clusters e Hubs Industriais de CCUS no Nordeste Brasileiro por Análise de Dados Geoespaciais Autor(es): Souza, Jansen Cruz de Orientador: Oliveira, Gustavo Charles Peixoto de Abstract: The injection and permanent storage of CO2 are critical operations in the Carbon Capture, Utilization, and Storage (CCUS) chain, essential for osetting emissions in hard-to-abate sectors such as energy and industry. Brazil’s Northeast region—particularly the states of Bahia (BA), Rio Grande do Norte (RN), Sergipe (SE), and Alagoas (AL) oers a highly favorable scenario for CCUS implementation due to its concentration of industrial hubs, existing oil well infrastructure in highly prospective sedimentary basins, and strategic logistics. This study identies CCUS clusters and hubs in these states using opportunity metrics based on emission density, transport feasibility, and the reuse of wells with an opportunity index (Ow) greater than 0.3 as CO2 sinks. The Potiguar (RN), Recôncavo (BA), and Sergipe-Alagoas (SE/AL) basins were analyzed, selected for their proven storage capacity. The methodology included mathematical models for screening municipalities by emissions and geospatial analysis. This study contributes to the assessment of the feasibility of scalable geological carbon storage projects in the Northeast, highlighting the integration of legacy infrastructure with new economic opportunities for the oil and gas sector. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-05-19T00:00:00Z