https://repositorio.ifpe.edu.br/xmlui/handle/123456789/491 2026-08-14T00:14:39Z 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. 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. 2026-07-07T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2262 Análise comparativa de modelos em sistemas multi-agentes para geração de documentos analíticos. The evolution of Large Language Models has driven significant advances in the automation of intellectual tasks. However, the reliability of their responses and their tendency to produce hallucinations remain relevant limitations for their use in professional contexts. This work presents a detailed comparative analysis of the performance of three models: GPT-4o-mini, Llama 3–8B, and Llama 3–70B. These models were applied to two distinct case studies: (i) the validation of an academic text with a focus on detecting inconsistencies and hallucinations, and (ii) the comparative financial analysis of multiple balance sheets. To conduct the experiments, a multi-agent system was developed using the CrewAI framework to orchestrate autonomous agents responsible for generating, reviewing, and validating documents. The methodology employs a structured verification pipeline based on manually created checklists, allowing the comparison of model outputs against the original documents and enabling the assessment of their accuracy. The results reveal significant differences among the three models in terms of content fidelity, textual clarity, analytical consistency, and hallucination rates, demonstrating that proprietary and open-source models exhibit distinct behaviors depending on the nature of the task. 2026-04-15T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2260 Classificação de pneumonia em radiografias pediátricas com deep learning e inteligência artificial explicável: uma análise comparativa entre as arquiteturas ResNet50 e YOLOv11s-cls. Pneumonia is one of the leading causes of child morbidity and mortality worldwide, and early diagnosis through chest X-rays is essential to reduce clinical complications. In this context, the use of deep learning techniques has shown promise as a tool to support medical diagnosis. This work proposes a comparative analysis between the YOLOv11s-cls and ResNet50 models applied to binary pneumonia classification in pediatric chest X-rays, using the Pediatric Pneumonia Chest X-ray Dataset, composed of 5,856 images divided into Normal and Pneumonia classes. Both models were trained with weights pre-trained on the ImageNet dataset using a two-phase progressive transfer learning strategy, combined with data augmentation techniques and class weight balancing to mitigate class imbalance. Performance evaluation was conducted using metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. Additionally, the Explainable Artificial Intelligence technique Gradient-weighted Class Activation Mapping was applied to investigate model explainability, identifying the X-ray regions that most influenced predictions. The results demonstrated that both models achieved high performance, with AUC-ROC values above 0.99. ResNet50 obtained superior performance across all evaluated metrics. 2026-07-07T00:00:00Z