https://repositorio.unifei.edu.br/jspui/handle/123456789/87 2026-11-12T22:34:25Z https://repositorio.unifei.edu.br/jspui/handle/123456789/3173 Título: Aquisição e validação de sinal de ruído eletroquímico Abstract: Corrosion is a global problem, which implies costs in industrialized countries of up to 4.5% of GDP, with either economic, but also social and environmental impacts. In the case of Brazil, the waste of water supply networks due to leaks loss is quite significant and much of it is caused by network degradation, indicating that corrosion control should be promoted whenever possible. This study proposes a corrosion monitoring system, in system subject to the use of inhibitor, with the approach of passive technique for monitoring corrosion by electrochemical noise (EN), in which the classification of events in a corrosion sensor by EN is part of methodological study for structural integrity (or “health”) monitoring system (SHM). Due to very dynamic and stochastic nature of the signal, this study and analysis of EN measurements (ENM) considers numerical and graphic characteristics of two corrosion systems both in saline aqueous solution: carbon steel and stainless steel. These experiments are repeated for accumulating data, which allow the generation of several graphs in time and frequency domains, from which at least one characteristic is extracted, which has a good correlation with data from corrosion processes. Then, based on a supervised machine learning system, the training data allows the model to be calibrated. From the test data, the correctness rate of the model above 50% is verified. Tipo: Dissertação 2022-02-17T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4489 Título: Desenvolvimento e tecnologias: cartografando controvérsias do sistema de arrecadação do imposto sobre serviço de qualquer natureza em Monsenhor PAULO/MG Abstract: This study analyzes the tax collection and inspection system of the Tax on Services of Any Nature (ISSQN) within the Finance Department of the Municipality of Monsenhor Paulo/MG, under the perspective of Actor-Network Theory (ANT). The general objective is to understand the sociotechnical relations involved in the constitution of networks of the ISSQN collection and inspection system in the aforementioned municipality, particularly in light of the growing digitalization of tax obligations. The research investigates how these interactions shape administrative practices, power relations, and the structure of the collection system, examining how tax digitalization, through the ISSWeb platform, reconfigures roles, institutional practices, and power relations in the municipal tax field. The theoretical framework adopted is Actor-Network Theory, developed by Michel Callon, Bruno Latour, and collaborators, and the methodology employed is Controversy Mapping, aimed at mapping human and non-human actors, their interactions, and the tensions emerging from the collection process. The methodological path is structured in five stages: (i) literature review on tax collection, digital platforms, and ANT; (ii) direct observation of the municipal collection system, focusing on ISSWeb operations for issuing invoices and tax declarations; (iii) semi-structured interviews with tax auditors, accountants, and taxpayers, aimed at capturing perceptions, disputes, and negotiations around the use of digital platforms; (iv) analysis and mapping of controversies, identifying conflicts, doubts, and negotiations among actors and the ways in which they mobilize, resist, or align; and (v) construction of the network of actants and description of results, integrating human and non-human actors and highlighting interdependencies, roles, and reciprocal influences. The research sources include federal and municipal legislation, administrative records, technical documents, and interview reports. The results indicate that ISSQN, beyond its strictly fiscal function, operates as an element of social organization, materializing as a hybrid network that articulates legal frameworks, tax technologies, and social actors. Ultimately, the study aims to provide a dense description of these interactions and contribute to the understanding of the role of municipal taxation in the financial autonomy of small municipalities, as well as to the broader debate on the sociotechnical effects of digitalization in public administration. Tipo: Dissertação 2026-07-06T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4488 Título: Autodrill: framework autoML para previsão da taxa de perfuração em poços de petróleo Abstract: Predicting the Rate of Penetration (ROP) plays a central role in optimizing operations in the oil and gas industry, directly influencing operational efficiency and drilling-related costs. However, conventional machine learning models have limitations in this context due to the strong non-linearity of the variables involved and, above all, the high lithological heterogeneity and low reliability of downhole sensors, resulting in noisy and gapped time series. This work proposes AutoDrill, an Automated Machine Learning (AutoML) framework specifically designed for the drilling domain. In contrast to generalist approaches, AutoDrill incorporates a preprocessing pipeline specialized in drilling signals (including adaptive smoothing, transient correction, and data interpolation) coupled with an automated hyperparameter search and tuning mechanism. The experimental evaluation was conducted on various datasets and geological scenarios, using records from three offshore repositories (Equinor Volve, USROP, and NEATS NOPIMS). The performance of AutoDrill was compared to the AutoGluon and H2O AutoML frameworks, considered representative of the state of the art in AutoML. The results indicate that AutoDrill exhibits consistent and competitive performance, achieving an average coefficient of determination (R2) of 0.91 across all analyzed scenarios, particularly in environments characterized by high heterogeneity and noise, such as in the case of NEATS NOPIMS. In this specific scenario, AutoDrill significantly outperformed the reference frameworks, reducing the mean absolute error (MAE) by up to 80% and raising the R2 from levels below 0.20 to 0.94. In conclusion, the systematic incorporation of domain knowledge into the machine learning automation cycle is crucial for the robustness of real-time prediction. From this perspective, AutoDrill presents itself as a practical, scalable, and domain-oriented approach for ROP prediction, contributing to the advancement of machine learning techniques in petroleum engineering. Tipo: Dissertação 2026-09-04T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4487 Título: Ferramenta web gamificada para o estudo introdutório de análise de dados Abstract: The growing volume of data generated globally across diverse activities is accompanied by an equally increasing demand to interpret it and extract valuable information. In this scenario, data analysis, an essential component of the Data Science domain, enables this process by transforming raw data into useful knowledge for decision-making. However, as students develop analytical skills, they face challenges such as subjective interpretation of visualizations, high-dimensional data, the need to understand sometimes abstract statistical concepts, and the required proficiency with specific computational tools. These factors point to the need for methodologies and tools that can support teachers and motivate students in this field. In this context, the research proposes developing a gamified web tool to support introductory data analysis. The tool aims to facilitate the study of concepts and data analysis techniques through a solution that incorporates game elements and was evaluated by volunteer students in computer science courses at the Federal University of Itajubá. The evaluation captured students’ perceptions of the developed tool from multiple perspectives. The results of this evaluation indicated high rates of usability, acceptance, and satisfaction. Tipo: Dissertação 2026-08-11T00:00:00Z