https://repositorio.uema.br/jspui/handle/123456789/1907 2026-07-09T03:21:38Z https://repositorio.uema.br/jspui/handle/123456789/6279 Título: Estimativas de arrecadação do ICMS do Estado do Maranhão usando algoritmos de machine learning Abstact: Tax collection forecasting is a cornerstone of fiscal planning and efficient public management. The Tax on Circulation of Goods and Services (ICMS) constitutes the main source of revenue for Brazilian states, and its accurate projection is crucial for allocating resources to strategic areas. However, the complexity of its dynamics, influenced by non-linear macroeconomic variables, and the lack of studies applied to the reality of the state of Maranhão pose a challenge for public administrators. This work aims to address this gap by investigating how machine learning techniques can improve the accuracy of forecasting monthly ICMS revenue in Maranhão. The overall objective is to develop and validate advanced computational models using a historical series of economic and social data from January 1997 to April 2024. This quantitative and applied research adopted the CRISP-DM framework. Data were collected from public sources such as SEFAZ-MA, IBGE, and the Central Bank. Initially, nineteen independent variables were considered, and a Multiple Linear Regression model was used to select the most relevant ones, such as GDP, diesel consumption, and electricity consumption indicators. Four machine learning algorithms were implemented, compared, and validated: Random Forest, Decision Tree, Linear Regression, and XGBoost. Performance evaluation was performed using the RMSE, MAE, MAPE, SMAPE, and R² metrics, using the k-fold cross-validation technique (with k=10) and a data split of 80% for training and 20% for testing. This study contributes a practical and validated model that can be integrated into the state's budget planning process, promoting more transparent, efficient, and data-driven fiscal management 2025-01-01T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6273 Título: Método computacional para auxiliar o diagnóstico precoce da Granulomatose de Wegener Abstact: This paper presents a proteomic pattern recognition system aimed at assisting in the early diagnosis of Wegener's Granulomatosis (WG), a rare idiopathic vasculitis that is difficult to detect and carries a high mortality rate for untreated individuals. The proposed method involves extracting features from proteomic signals and classifying them as belonging to individuals with or without WG. To achieve this, Independent Component Analysis is used for feature extraction, the Minimum Redundancy Maximum Relevance algorithm is employed to reduce the number of features and computational costs, and a Support Vector Machine is used for classification. The method's performance was evaluated using a dataset of 335 proteomic signals, comprising 75 active cases, 101 negative cases, and 159 cases in remission. The best result was obtained using a twenty-feature vector, yielding accuracy, specificity, and sensitivity of 98.24%, 99.73%, and 99.50%, respectively. These results demonstrate that the proposed system is efficient for diagnosing WG and outperforms the current methodology, which is based on clinical, serological, and radiological examinations proposed by the American College of Rheumatology. 2016-07-22T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6247 Título: Sistemas de gerenciamento e monitoramento de rack’s outdoors de telecomunicações, baseado em internet of things Abstact: The present work aims to correlate concepts, technologies and application of a solution based on embedded systems, Internet Of Things and 5G, to monitor and ensure data persistence in telecommunications companies. First, a survey of the current scenario of the Telecommunications industry is carried out. In addition, they present intrinsic problems, in which consumers are the most affected, such as the lack of reliability and interactivity of the product offered by energy concessionaires. The bibliographic research was through a literary review based on articles, books and works by several authors from the period 2019 to 2022. The collection of information on the topic took place through the databases: Google Scholar and IEEE. In this way, conceptual information was presented on technologies such as ESP32, 5G, sensing and especially the MQTT protocol, for long-distance solutions, which belong to the concept of Internet of Things (IoT). Therefore, we propose the development of a device capable of monitoring and assisting telecommunications companies in the management to maintain their external assets. 2022-10-31T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6236 Título: Processamento de documentos jurídicos longos: comparação e avaliação de métodos baseados em Modelos de Linguagem Abstact: The Brazilian legal system faces a structural scenario of accumulating lawsuits, which compromises its efficiency and adherence to the constitutional principle of a reasonable trial duration. As of August 2024, the number of pending cases exceeded 80 million, according to data from the Judiciary's National Database. This substantial volume of litigation directly impacts the speed and effectiveness of judicial service delivery, necessitating the development of technological tools capable of supporting the management, screening, and comprehension of legal documents—documents whose length and complexity challenge traditional human and automated analysis workflows. In this context, understanding how advanced text processing techniques can contribute to streamlining judicial activity lies at the heart of this dissertation. Existing applications in the field, such as BumbaBERT, show promising results for optimizing procedural workflows but remain constrained by the structural limitations of their underlying Transformer architecture, particularly due to high computational complexity. To address this issue, this dissertation project proposes and evaluates a set of strategies aimed at the efficient processing of long documents, using initial complaints linked to Incidents for the Resolution of Repetitive Demands (IRDR) as a case study. Building on gaps identified in the literature and the practical motivation stemming from the UEMA-TJMA technical cooperation agreement—specifically regarding the difficulty of adapting language models to extensive legal texts—the methodological process was guided by the Data Science Trajectories (DST) framework. This approach provided a foundation for understanding the domain and planning solutions, as well as for identifying a taxonomy of methods capable of organizing the field of automatic long-document classification into three categories: truncation methods derived from baselines (e.g., BumbaBERT, LegalBERT-PT); ...decomposition-recomposition (e.g., ToBERT) and content synthesis based on sentence selection strategies (e.g., TextRank, LexRank, SBERT, LlaMa). Based on this framework, empirical experimentation and statistical validation were conducted. Consequently, the study involved implementing and comparing eight architectures based on fine-tuning BumbaBERT—totaling 40 experiments—that considered performance metrics such as accuracy, F1-score, precision, and recall; computational efficiency indicators such as time, inference speed, and memory usage; statistical significance tests; and practical implementation feasibility. The results demonstrated that hierarchical architectures outperform content synthesis-based approaches, achieving a better balance between precision and stability, albeit at a higher computational cost. This finding reinforces the importance of preserving the integral argumentative structure of legal texts to ensure interpretive consistency and the reliability of automated classifications. Thus, the work contributes scientifically to the advancement of natural language processing in the legal domain by demonstrating how established strategies can be reinterpreted and adapted to address the linguistic and structural specificities of Brazilian legal texts. From a technological and institutional perspective, the study offers a reproducible artifact capable of integration into the TJMA’s automation system, thereby contributing to reduced case processing times and the strengthening of digital transformation policies in the public sector. Finally, regarding the social dimension, the study reaffirms the role of digital transformation as a tool for democratizing access to justice, fostering innovation that combines technical precision, ethical responsibility, and a commitment to the public interest. 2025-11-12T00:00:00Z