Navegando por Assunto "CNN (Convolutional neural network)"

Agora exibindo 1 - 2 de 2

Acesso aberto (Open Access)
Detecção de erosão em taludes baseada em deep learning
(Universidade Federal do Pará, 2023-03-31) LIMÃO, Caio Henrique Esquina; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
The recent catastrophes triggered by the rupture of the Fundão and Córrego do Feijão dams caused around 300 deaths and countless irreparable socio-environmental damages. Since the use of more accurate monitoring systems and the proper execution of preventive and corrective maintenance would allow identifying, and even mitigating, the damage caused to society, it can be stated that there is a need for greater investment and incentive to create solutions of Structural Health Monitoring (SHM) capable of diagnosing occurrences that compromise the most crucial civil structures, such as bridges, buildings, dams and slopes. High-performance Artificial Intelligence (AI) techniques have been able to solve these structural analysis problems and presented superior results to previous solutions, their use has increased dramatically in the most diverse (SHM) scenarios. When it comes to image analysis and classification solutions, Convolutional Neural Network (CNN) is the type of neural network that delivers the best results. Therefore, this dissertation will describe the development process of a CNN with three convolutional layers that combines the use of the most consolidated technologies in the current scenario of computer vision, such as the Adam optimizer and batch normalization. The proposed CNN was trained with a database set up specifically for this dissertation, consisting of images of public work reports made by the Brazilian government, portfolios of companies that work with construction and maintenance of slopes and reports on landslides and/or catastrophes. These images were labeled, according to the context of each one of them, as stable or instable slopes. The results obtained were quite satisfactory, presenting an accuracy of 96.67% and proving that this solution is capable of identifying in a precise and improved way the instability indicators presented by the analyzed slopes, allowing a more adequate planning of the maintenance for each case, in the prevention of possible disasters, more efficient manpower management, cost reduction, greater safety and structural health to ensure its long-term integrity.
Acesso aberto (Open Access)
Redes Neurais Convolucionais para Auxiliar no Diagnóstico de Exames Preventivo de Colo de Útero.
(Universidade Federal do Pará, 2024-09-18) COSTA, Edriane do Socorro Silva; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
The cervical screening exam is a widely used method to detect cervical cancer and precancerous lesions. Automated classification of the results can assist healthcare professionals in accurately identifying abnormal cytology patterns, increasing accuracy and consistency in detecting anomalies. Furthermore, systematizing this solution can reduce analysis time and associated costs, enabling the provision of an immediate pre-diagnosis, especially in remote areas. This approach also has the potential for integration into public health systems, contributing to more efficient and accessible care. Therefore, this study proposes the application of pre-trained convolutional neural network models VGG16 and VGG19 for classifying images resulting from the liquid-based cytology technique, comparing the performance of 4-class versus 2-class classification with balanced and unbalanced data. Several architectures were tested, and accuracies of up to 98% were achieved, along with good classification metrics, showing potential as a solution to assist healthcare professionals in more assertive classification of these results.