https://tedebc.ufma.br/jspui/handle/tede/279 Mon, 13 Apr 2026 14:06:16 GMT 2026-04-13T14:06:16Z http://tede2.ufma.br:8080/jspui/retrieve/276/NEWSb37b0c05ba.png https://tedebc.ufma.br/jspui/handle/tede/279 https://tedebc.ufma.br/jspui/handle/tede/6900 Título: Classificação de Exames PET de Corpo Inteiro usando Representações MIP e Aprendizado Profundo Autor: SOARES FILHO, Celso Luiz Silva Primeiro orientador: PAIVA, Anselmo Cardoso de Abstract: Cancer is one of the greatest global public health challenges, with an estimated 35 million new cases by 2035. In this context, Positron Emission Tomography (PET) is essential for diagnosis and monitoring. However, the clinical interpretation of these exams is an exhaustive task, subject to the specialist’s subjectivity and limited by the high complexity of 3D volumetric data. This work proposes a method for the automatic classification of whole-body PET scans of patients with lung cancer, lymphoma, melanoma, and healthy individuals, using deep learning techniques applied to Maximum Intensity Projection (MIP) representations. The method is structured in four stages: generation of MIP images in the coronal and sagittal axes, preprocessing, feature extraction, and classification. Six architectures for feature extraction (ConvNeXt, EfficientNet-B0, Swin, and VGG19) and three classifiers (MLP, SVM, and XGBoost) were evaluated. The method achieved results of 96.45% for the AUC metric, 91.98% for the accuracy, 91.63% for the F1-Score, 91.18% for the sensitivity, and a precision of 92.08%. These results show that the use of MIP representations, combined with a set of perspective-specific specialized architectures, allows for satisfactory performance, approaching approaches that use 3D volumes and hybrid examinations (PET/CT). Instituição: Universidade Federal do Maranhão Tipo do documento: Dissertação Fri, 13 Mar 2026 00:00:00 GMT https://tedebc.ufma.br/jspui/handle/tede/6900 2026-03-13T00:00:00Z https://tedebc.ufma.br/jspui/handle/tede/6899 Título: Sistema de Apoio ao Diagnóstico do Risco de Transtorno de Ansiedade em Crianças Autor: ROCHA, Renata Costa Primeiro orientador: BARROS FILHO, Allan Kardec Duailibe Abstract: Childhood anxiety disorders represent a significant mental health concern, particularly due to the challenges associated with early identification, the subjectivity of clinical assessment instruments, and the overlap of behavioral patterns. In this context, computational approaches have been investigated as decision-support tools, especially those based on machine learning techniques applied to psychometric data. However, such approaches still face challenges related to decision robustness, clinical interpretability, and consistent performance in ordinal multiclass scenarios. To address these limitations, this work proposes a computational decision-support system for binary and multilevel classification of anxiety disorder risk in children, grounded in supervised learning models from the perspective of Electrical Engineering applied to mental health. Three established models are comparatively evaluated — Random Forest, Support Vector Machine, and Multilayer Perceptron — considering a binary screening scenario and an ordinal multiclass scenario composed of four risk levels. The methodology employs a public dataset from the Harvard Dataverse, consisting of psychometric, behavioral, and psychosocial information, and is validated through stratified cross-validation and performance metrics aligned with clinical practice, including explicit analysis of ordinal clinical error by distinguishing adjacent and non-adjacent misclassifications. The results indicate that the models achieve high discriminative capacity in the binary scenario (AUC values above 0.94) and consistent performance in the multiclass scenario (overall accuracy between 83% and 85%), with no universally superior classifier. A complementary behavior among the architectures is observed, with Random Forest demonstrating greater global stability and Multilayer Perceptron showing improved discrimination between intermediate risk levels. It is concluded that classical supervised models, when properly validated, constitute promising tools for the ordinal stratification of pediatric anxiety risk. From an Electrical Engineering perspective, the problem is characterized as a latent state inference process based on noisy and partially observable data, contributing methodologically to the development of interpretable computational decision-support systems in child mental health. Instituição: Universidade Federal do Maranhão Tipo do documento: Dissertação Tue, 10 Mar 2026 00:00:00 GMT https://tedebc.ufma.br/jspui/handle/tede/6899 2026-03-10T00:00:00Z https://tedebc.ufma.br/jspui/handle/tede/6850 Título: UM FRAMEWORK BASEADO EM DATA LAKEHOUSE PARA ARMAZENAMENTO, ANÁLISE E INTEGRAÇÃO DE DADOS EM SISTEMAS ENERGÉTICOS RENOVÁVEIS Autor: IBANEZ, Juan Daniel Ferreira Primeiro orientador: LOPES, Denivaldo Cícero Pavão Abstract: This dissertation proposes FIDLER, a Data Lakehouse-based framework for storing, integrating, and analyzing renewable energy data, focusing on wind and tidal resources in the state of Maranhão, Brazil. The research is driven by the need for efficient solutions to handle the heterogeneity, volume, and variety of data generated by measurement equipment such as LIDAR, SODAR, ADCP, and micrometeorological towers. The architecture is structured in Bronze, Silver, and Gold layers, preserving the temporal semantics of energy data while promoting governance, scalability, and integration with modern analytical tools. The study includes database extensions such as TimescaleDB and PostGIS to optimize queries and support georeferencing, and it defines specific strategies for ingesting, standardizing, and enriching the data. The framework is validated using real-world campaigns conducted in Maranhão, demonstrating its potential to support time-series analysis, generation forecasting, and decision-making for the regional energy transition. Instituição: Universidade Federal do Maranhão Tipo do documento: Dissertação Fri, 30 Jan 2026 00:00:00 GMT https://tedebc.ufma.br/jspui/handle/tede/6850 2026-01-30T00:00:00Z https://tedebc.ufma.br/jspui/handle/tede/6821 Título: Fluxo de potência ótimo por sensibilidade de carbono para minimizar custos operacionais e emissão de gases de efeito estufa Autor: RIBEIRO, Kayo Jorge Ammirati Primeiro orientador: PAUCAR CASAS, Vicente Leonardo Abstract: Carbon emission trading constitutes a pivotal market-based instrument for mitigating greenhouse gas (GHG) emissions by establishing economic signals that drive investments and operations toward lower carbon intensity. In this context, organizations have adopted Internal Carbon Pricing (ICP) as a governance mechanism to prioritize low-emission technologies and projects. However, traditional carbon accounting approaches often fail to adequately capture the physics and operational constraints of power grids, thereby limiting the spatial and operational interpretation of emissions. To address this gap, this work proposes and applies the Carbon-Sensitive Optimal Power Flow (CS-OPF), formulated as an extension of the conventional Optimal Power Flow (OPF) that explicitly integrates environmental criteria into the dispatch optimization through carbon pricing. To quantify and interpret the environmental impacts associated with operational decisions and the location of injections/consumption, carbon intensity and sensitivity metrics are employed, with an emphasis on Locational Marginal Emissions (LME) and Life Cycle Assessment (LCA). Model simulations and validations are conducted on the IEEE 118-bus test system using the MATLAB/MATPOWER environment, enabling an evaluation of the trade-off between operational costs and emissions under various carbon price scenarios. The results indicate that the explicit inclusion of carbon in the optimization process shifts the optimal generation allocation and can significantly reduce emissions while maintaining a technically consistent and economically viable operation, reinforcing the method's applicability in supporting regulatory and operational decisionmaking. Instituição: Universidade Federal do Maranhão Tipo do documento: Dissertação Mon, 26 Jan 2026 00:00:00 GMT https://tedebc.ufma.br/jspui/handle/tede/6821 2026-01-26T00:00:00Z