https://repositorio.ifpe.edu.br/xmlui/handle/123456789/495 2026-04-25T05:47:15Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2056 ANS2JSON: uma API baseada em IA, para extração de Informações da avaliação neurológica de pacientes com hanseníase The Simplified Neurological Assessment (SNA) is a mandatory and essential tool for monitoring patients with leprosy in Brazil. However, its physical format and manual completion represent a significant obstacle, as they confine crucial clinical data to paper records and hinder longitudinal analyses, large-scale research, and evidence-based health policymaking. This study introduces ANS2JSON, an innovative application that overcomes this barrier through a hybrid Artificial Intelligence architecture for the complete and automatic digitization of SNA forms. The proposed solution addresses the challenge of interpreting a complex form that combines textual data with visual diagrams by employing a two-stage pipeline: (1) a computer vision model (YOLOv8 + Random Forest) to detect and anatomically map sensitivity assessment points, and (2) an Intelligent Document Processing model to extract textual fields. The approach demonstrated outstanding effectiveness, achieving 97.5% precision in visual data interpretation and over 95% accuracy in extracting key clinical indicators. ANS2JSON, publicly available via the web, provides a robust tool for converting a vast repository of unstructured data into ready-to-use digital information, unlocking the potential of years of clinical records to advance both leprosy treatment and research. The application is accessible at: https://ans2json.dotlabbrazil.com.br . 2025-09-16T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/1988 Contagem automática de ovos de mosquitos Aedes em ovitrampas com visão computacional baseada em aprendizado de máquina The present study proposes the automation of egg counting for Aedes aegypti and Aedes albopictus mosquitoes, vectors of arboviruses, through computer vision based on machine learning. Using images from ovitraps provided by Fiocruz-PE, fine-tuning was applied to advanced models (YOLOv10, YOLOv11, and Faster R-CNN) to overcome challenges related to high variability and noise in the images. The solution reduces manual effort and analysis time, contributing to more effective strategies for controlling diseases such as dengue, zika, and chikungunya. 2025-11-13T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/1984 Projeto e validação teórica de um sistema automatizado para análise da permeabilidade e respiração do solo An essential physical characteristic that controls soil aeration, gas exchange between the soil and the atmosphere, and biological activity in the rhizosphere is soil air permeability (Ka). The precise assessment of this characteristic is fundamental to determine the structural quality of the soil, identify compaction problems, and improve agricultural management practices. However, conventional methods for measuring air permeability in the field are often complex, expensive, and laborious. This study describes the design, theoretical validation, and proposed use of a low-cost, automated pneumatic infiltrometer, conceived to analyze soil air permeability in various situations of structural alteration and initial moisture. The main objective was to propose and detail a device capable of injecting a controlled airflow onto the soil surface and, based on the measurement of the resulting pressure, estimate air permeability. The proposed approach is based on a prototype using the ESP32 microcontroller, a MPXV7002DP differential pressure sensor for permeability analysis, and a carbon dioxide (CO₂) MH-Z19 sensor for soil respiration studies. For the future validation of the prototype, an analysis of the impact of structural disturbance and moisture on permeability is proposed, as well as the quantification of CO₂ efflux. The theoretical analysis indicates that compaction and moisture significantly reduce Ka . It is concluded that the project is an effective and innovative multifunctional platform for research in soil physics and biogeochemistry, offering a rapid and economical method to evaluate the structure and biological activity of the soil in situ. 2025-10-20T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/1983 Aplicativo móvel para a identificação automática dos principais vetores da doença de chagas no Estado de Pernambuco Chagas disease is considered by the World Health Organization as a neglected disease and a serious public health problem, with approximately 7 million people currently infected by Trypanosoma cruzi worldwide. The objective of this work was to develop an application for the Android platform that uses a machine learning model to help identify images of triatomines that are vectors of the Chagas disease. The model used was based on EfficientNetV2, a convolutional neural network architecture pre-trained for generic image recognition, which was enhanced with images of native vectors from Pernambuco and similar non-vector insects. The developed model was evaluated using a test dataset distinct from those used in training and validation, achieving an accuracy of 91.89%. These results indicate that the adapted EfficientNetV2 model was able to generalize well to new data. The application, named TriatoDetect, was designed with an interface to facilitate the identification of triatomines through the phone's camera or images stored on the device. 2025-09-04T00:00:00Z