https://repositorio.uema.br/jspui/handle/123456789/1885 Thu, 09 Jul 2026 02:18:17 GMT 2026-07-09T02:18:17Z http://repositorio.uema.br:80/jspui/retrieve/81630c2c-ff88-4675-815a-b0db45be13a1/CCT UEMA.png https://repositorio.uema.br/jspui/handle/123456789/1885 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 Wed, 01 Jan 2025 00:00:00 GMT https://repositorio.uema.br/jspui/handle/123456789/6279 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. Fri, 22 Jul 2016 00:00:00 GMT https://repositorio.uema.br/jspui/handle/123456789/6273 2016-07-22T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6250 Título: Automatização do reconhecimento de células germinativas em imagens histológicas de ovários de peixes: estudo de caso de peixes encontrados no estado do Maranhão Abstact: The state of Maranhão has significant fishing activity, making it essential to monitor the reproductive biology of fish for sustainable management. This work presents an automated approach for recognizing germ cells in histological images of fish ovaries, using digital image processing and supervised learning. The objective is to develop a tool that aids in the efficient analysis of gonads, contributing to knowledge in the field and better management of fishing resources. The methodology uses the Canny edge detection algorithm to segment cells and supervised learning techniques to classify them, overcoming the limitations of traditional manual methods. The results show gains in batch processing speed (50 images/minute) and precision (56% accuracy) with STERapp. The solution aims to increase the precision and reproducibility of analyses, positively impacting fishing sustainability in Maranhão and similar regions Mon, 17 Feb 2025 00:00:00 GMT https://repositorio.uema.br/jspui/handle/123456789/6250 2025-02-17T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6249 Título: Sistema Web para delegacias com geração de imagens fotorrealistas baseadas em Inteligência Artificial a partir de relatos textuais Abstact: This work presents the development of a web application designed for police station management, focusing on integrating artificial intelligence (AI) to generate photorealistic images from textual descriptions to enhance criminal investigations. Built on a client-server architecture, the system employs Next.js for the front-end, Flask for the back-end, and the Stable Diffusion model for image generation. The methodology combined applied, exploratory, and experimentais approaches with incremental prototyping to ensure scalability and usability. Requirements analysis identified gaps in virtual police station systems, such as the lack of advanced visual tools, guiding the development of features like creation, management, and finalization of incident reports, secure JWT authentication, and AI integration. System modeling utilized UML, including use case, class, sequence, activity, and deployment diagrams. Integration and functional tests, conducted with tools like Postman and Cypress, validated the application's efficiency and robustness. The results demonstrate that the system meets its objectives, providing an innovative solution that streamlines suspect identification and improves incident reporting efficiency, with potential for future integration with biometric databases and further AI model adaptation Thu, 01 Jan 2026 00:00:00 GMT https://repositorio.uema.br/jspui/handle/123456789/6249 2026-01-01T00:00:00Z