TCC - Bacharelado em Ciência da Computação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415
Navegar
2 resultados
Resultados da Pesquisa
Item Avaliação da performabilidade do sistema ferroviário da região do Recife(2024-03-08) Santos Júnior, Rodemarck Melo dos; Callou, Gustavo Rau de Almeida; http://lattes.cnpq.br/3146558967986940; http://lattes.cnpq.br/5274177344296463The rail system in the Recife region can transport approximately 400,000 passengers daily. Failure drastically decreases its carrying capacity. An example of a failure that occurs frequently is the so-called false occupancy failure. False occupancy failures occur when the train detection mechanism for part of the route is defective, forcing the driver to take manual control, increasing the risk of accidents. One of the solutions is to increase the capillarity of the railway system by adding alternative routes. In this context, this work proposes a set of models for evaluating the performability of railway systems. A case study using the Recife railway system was used to show the applicability of the proposed models, where it was possible to increase the system availability by practically 50% with the addition of alternative routes, also improving the performance metrics.Item Uma metodologia para a avaliação de desempenho e custos do treinamento de redes neurais em ambientes de nuvem(2024-03-07) Moura Filho, Cláudio Márcio de Araújo; Sousa, Érica Teixeira Gomes de; http://lattes.cnpq.br/9899077867723655; http://lattes.cnpq.br/8143173691280119Deep neural networks are solutions to problems involving pattern recognition and several works try to find ways to optimize the performance of these networks. This optimization requires suitable hardware to be implemented, hardware that can be very expensive for small and medium-sized organizations. The objective of this work is to propose a methodology to evaluate the performance and cost of training neural networks, considering the factors that most impact training time and evaluate the total financial cost of the environment for this task. In this sense, it was observed that factors such as the size of the input image and the network architecture have a great impact on the training time metric and consequently on the total cost.