https://repositorio.ifpe.edu.br/xmlui/handle/123456789/492 Mon, 24 Aug 2026 16:06:03 GMT 2026-08-24T16:06:03Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2295 Ciência de dados aplicada ao mercado de trabalho de Pernambuco: processamento e visualização dos microdados da PNAD Contínua. This study describes the development of a Data Science-based solution applied to the acquisition, processing, integration, analysis, and visualization of microdata from the Continuous National Household Sample Survey (PNAD Contínua), conducted by the Brazilian Institute of Geography and Statistics (IBGE). The study focuses on exploring the characteristics and structural inequalities of the labor market in the state of Pernambuco, Brazil, from 2019 to 2025. The methodological approach involved the automated collection of microdata from the IBGE portal through a pipeline implemented in Python, as well as the local extraction and management of compressed files and the processing of fixed-width data into structured datasets using the pandas and numpy libraries. The results followed both an analytical and a technological approach. From the analytical perspective, exploratory data analysis revealed sociodemographic and income inequalities within the state. From the technological perspective, an interactive web application was developed using the Streamlit framework and the Plotly library, enabling the dynamic exploration of labor market indicators and access to socioeconomic information about the state. The study demonstrates the effectiveness of technology as an agile social diagnostic tool to support the investigation of the characteristics and inequalities present in the labor market. Wed, 19 Aug 2026 00:00:00 GMT https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2295 2026-08-19T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2293 Análise comparativa de modelos de aprendizado de máquina para classificação de corridas rentáveis em plataformas de transporte. The growth of digital urban transportation platforms has increased the amount of data generated about trips, fares, distances, schedules and operational characteristics. Although these data are widely available, drivers and other actors involved in platform-based transportation still face difficulties in converting information into effective decision support, especially when the purpose is to evaluate whether a ride tends to be profitable or not. In this context, this study aims to analyze and compare machine learning (ML) models for classifying profitable and non-profitable rides using two distinct datasets: an Uber/NCR-type ride-booking dataset and a public New York City Yellow Taxi dataset. The methodology was structured according to the CRISP-DM process, covering problem understanding, data understanding, data preparation, modeling and evaluation. Derived variables for estimated cost, estimated profit and profitability were created, together with a methodological discussion of data leakage risks, especially regarding financial variables. Sensitivity analyses were also included to assess the impact of variables directly related to the profitability calculation. The evaluated models included Logistic Regression, Decision Tree, Random Forest, Extra Trees, Gradient Boosting, AdaBoost, baseline models and a simple TensorFlow/Keras neural network as a complementary experiment. For the Uber/NCR dataset, Gradient Boosting achieved an approximate F1-score of 0.99, a result strongly associated with the presence of booking_value and ride_distance. For the Yellow Taxi NYC dataset, the complementary neural network and Random Forest achieved F1-scores close to 0.93, decreasing to 0.7735 when duration_min and avg_speed_mph were removed. The results indicate that ML models can support the identification of patterns associated with ride profitability, provided that dataset limitations, the estimated nature of the target variable and variable availability at decision time are explicitly considered. Thu, 09 Jul 2026 00:00:00 GMT https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2293 2026-07-09T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2269 Avaliação da eficácia de grandes modelos de linguagem na geração de planos de estudo personalizados baseados nos estilos de aprendizagem Honey-Alonso. Personalized learning has become an increasingly relevant topic due to the growing application of digital technologies in educational contexts. In this scenario, Large Language Models (LLMs) have shown potential to support the development of study plans tailored to students' individual characteristics. This study investigates the use of LLMs in the creation of personalized study plans based on the learning styles defined by the Honey- Alonso Learning Styles Questionnaire (CHAEA). To achieve this objective, an exploratory research approach was conducted, supported by a literature review on learning styles, artificial intelligence, and Large Language Models. The proposed methodology includes the definition of educational scenarios, the development of a standardized model for study plan generation, and the establishment of criteria for evaluating the materials produced by the analyzed LLMs. This research seeks to contribute to the understanding of the potential applications of generative artificial intelligence in education, particularly in the context of personalized learning and support for the learning process, providing a foundation for future investigations into the use of these technologies as educational support tools. Fri, 10 Jul 2026 00:00:00 GMT https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2269 2026-07-10T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2263 Desenvolvimento de um sistema de reconhecimento de placas veiculares para controle de acesso em ambientes residenciais. Access control in residential and commercial buildings has become a fundamental pillar in modern security management. This paper presents the development of an Automatic License Plate Recognition (ALPR) system designed to automate vehicle entry and exit flows. The proposed solution integrates the Python language with the OpenCV library for digital image preprocessing and the Tesseract OCR engine, based on Long Short-Term Memory (LSTM) neural networks, for character extraction. The system utilizes bilateral filtering for noise reduction while preserving edges and adaptive thresholding for segmentation, ensuring high accuracy even under variable lighting conditions. Data is managed by an SQLite database, offering a low-cost, high-efficiency serverless architecture. The results demonstrate the technical viability of replacing manual controls with computer vision systems on general-purpose hardware. Tue, 07 Jul 2026 00:00:00 GMT https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2263 2026-07-07T00:00:00Z