https://repositorio.unifei.edu.br/jspui/handle/123456789/87 Wed, 15 Apr 2026 16:46:54 GMT 2026-04-15T16:46:54Z 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 Thu, 17 Feb 2022 00:00:00 GMT https://repositorio.unifei.edu.br/jspui/handle/123456789/3173 2022-02-17T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4373 Título: Educação ambiental e conservação da natureza: uma análise de teses e dissertações Abstract: Faced with a potential environmental collapse and in an attempt to prevent it – or, at best, to minimize or mitigate the catastrophic effects of the changes we have been causing in natural dynamics – many alternatives have been proposed. Among these, Education for Nature Conservation (ENC), together with Environmental Education (EE), appears as a potential pathway for rethinking the society–nature relationship. In this context, the present research was guided by the following question:What possible meanings are being put into circulation, in theses and dissertations, regarding the relationship between Environmental Education and Education for Nature Conservation, involving biodiversity conservation processes with which certain communities establish, in some way, everyday relationships? Accordingly, this study aimed to analyze the statements found in theses and dissertations that problematize the relationship between EE and ENC, involving biodiversity conservation processes connected to communities’ daily lives. In order to seek possible answers and achieve the research objective, we adopted the theoretical and methodological framework of “State of the Art” studies, using the Fracalanza Platform of the EArte Project – of which this research is part – to identify relevant works. Data analysis was conducted in two stages: first, we mapped and described the scenario of 42 selected studies on ENC in dialogue with EE. In the second stage, 21 studies were submitted to analysis grounded in Braun and Clarke’s (2006) Thematic Analysis, enabling the identification of themes that were subsequently examined through approximations with Mikhail Bakhtin’s dialogical perspective. The analysis of the relationship between EE and ENC involving communities connected to biodiversity resulted in the identification of five themes: Sustainability, Management and Use of Natural Resources; Awareness-Raising for Conservation Actions; Participation and Empowerment; Dialogue of Knowledge; and the Dimension of Values: Ethics and Aesthetics. The analyzed statements reflect meanings that represent, reinforce, or challenge ideas of exploitation and domination of nature. At the same time, they present alternative perspectives that may – or may not – take into account aspects that distinguish socio-environmentalism from the earlier form of environmentalism associated with conservationist ideals, particularly by recognizing social presence, lived realities, and participation in conservation and educational processes. Thus, this research seeks to contribute to critical reflection on the statements circulating in the field of Environmental Education regarding the relationship between EE and ENC, and highlights the importance of further studies–whether “State of the Art” or otherwise – to deepen the various developments that may emerge from a detailed and critical reading of this dissertation. Tipo: Dissertação Tue, 10 Feb 2026 00:00:00 GMT https://repositorio.unifei.edu.br/jspui/handle/123456789/4373 2026-02-10T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4372 Título: Meta-otimização dos hiperparâmetros do algoritmo XGBoost para classificação binária: uma integração entre planejamento de experimentos e o método da interseção normal à fronteira Abstract: Hyperparameter tuning is decisive for both predictive performance and computational cost in machine learning models. In binary classification with Extreme Gradient Boosting, tuning is inherently multiobjective: predictive quality must be maximized while execution time is minimized. This work proposes a methodological framework that integrates Design of Experiments, Response Surface Methodology, Factor Analysis, and the Normal Boundary Intersection method to guide the selection of Extreme Gradient Boosting hyperparameters under a fixed evaluation budget. The initial exploration is conducted through a fractional facecentered central composite design, totaling 88 configurations. The observed responses (accuracy, precision, recall, specificity, and runtime) are collected under a reproducible protocol and summarized through factor scores obtained via principal component analysis with Varimax rotation. These scores define quality and cost objective functions, reduce redundancy among metrics, and support an interpretable assessment of trade-offs. Quadratic responsesurface models are then fitted to the objective functions and used by Normal Boundary Intersection to sample an approximately uniform Pareto frontier; candidate solutions are reevaluated on the real model, and a final compromise configuration is selected. The proposed approach is benchmarked, under equivalent evaluation budgets, against grid search, random search, Bayesian optimization, and Hyperopt. Results show substantial computational savings: the method achieves an average runtime of 0.078 s per fold and an average total runtime of 158 s, reducing total time by 9% to 71% relative to the benchmarks while maintaining high and stable predictive performance across replications. As external validation, the proposed pipeline was replicated on two additional datasets with contrasting profiles (balanced and highly imbalanced), reproducing the cost–quality trade-off observed in the canonical benchmark and reinforcing the multivariate stability of the method. Overall, integrating Design of Experiments and Normal Boundary Intersection provides a parsimonious, interpretable, and replicable alternative for multiobjective hyperparameter tuning, with potential applicability to other Gradient Boosting Decision Tree families and cost-constrained settings. Tipo: Dissertação Thu, 19 Feb 2026 00:00:00 GMT https://repositorio.unifei.edu.br/jspui/handle/123456789/4372 2026-02-19T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4371 Título: Detecção de trojans de hardware em circuitos combinacionais NCL através do método de transições probabilísticas Abstract: The interest in Quasi Delay Insensitive digital circuits, especially Null Convention Logic circuits, stems from the absence of a need for a global clock signal to control the circuit’s parts. This results in faster, energy-efficient, and more robust circuits. With the increasing demand for this type of circuit in the industry, undesirable modifications from malicious actors are a concern, given that the large-scale production process for these circuits is divided among various companies and collaborators, which makes it difficult to have complete knowledge of its entire production process. Given this context, this work aims to study and analyze the Probabilistic Transitions method applied to combinational Null Convention Logic circuits. The algorithm receives information about the interconnections of the original and modified circuits and compares, based on the values of each logic element, whether or not modifications occurred between the circuits, using the valid input value cases (“01” and “10”). Based on the discussions contained in this work, the following results are presented: functional descriptions and simulations of the test circuits; the implementation of a transpiler to convert Quartus software output files into the algorithm’s required netlist format; and the development of the probabilistic transition algorithm itself. The algorithm operates in two modes: when provided with a single netlist, it calculates transition values for all elements to generate a unique circuit signature; when provided with two netlists, the program performs individual calculations and executes a comparative analysis, reporting potential divergences and their specific locations. Tipo: Dissertação Tue, 24 Feb 2026 00:00:00 GMT https://repositorio.unifei.edu.br/jspui/handle/123456789/4371 2026-02-24T00:00:00Z