Trabalho de Conclusão de Curso - TCC

URI Permanente para esta coleçãohttps://repositorio.cesupa.br/handle/prefix/32

Navegar

Navegando Trabalho de Conclusão de Curso - TCC por Orientador "Ferreira, Fábio dos Santos"

Filtrar resultados informando as primeiras letras
Agora exibindo 1 - 2 de 2
  • Nenhuma Miniatura disponível
    Item
    Aplicação de um algoritmo genético para otimização do roteamento de veículos coletivos em rede
    (Centro Universitário do Estado do Pará, 2018-06-15) Almeida Neto, Adilson de; Ferreira, Fábio dos Santos; http://lattes.cnpq.br/4845857829374774; Pereira, Rodrigo Lisbôa; http://lattes.cnpq.br/0961152700140103; Souza, Daniel Leal; http://lattes.cnpq.br/6059334260016388
    Genetic algorithms are used in a wide range of optimization problems, especially in combinatorial problems, where the search space is, in many occasions, too large for exact methods to achieve optimal solutions. This class of problems bear great importance for mathematical models that reflect real world situations, such as vehicle routing. The goal of this work is to utilize a genetic algorithm to optimize networked linked capacitated vehicles, in this configuration, all passengers and drivers positions are known in every moment. To make this optimization possible, the problem was mathematically modeled using the Capacitated Vehicle Routing Problem (CVRP) as inspiration with alterations reflecting the nature of the network linked capacitated vehicles. After that, this work also compares the obtained performance to a non-optimized route, so that the gain from using this method can be observed.
  • Nenhuma Miniatura disponível
    Item
    Utilização de inteligência artificial para mapeamento de estradas não oficiais na Amazônia
    (Centro Universitário do Estado do Pará, 2020) Botelho Junnior, Jonas Paiva; Ferreira, Fábio dos Santos; http://lattes.cnpq.br/4845857829374774; Ribeiro, Moshe Dayan Sousa; http://lattes.cnpq.br/5200296393526606; Teixeira, Otávio Noura; http://lattes.cnpq.br/5784356232477760
    Mapping unofficial roads in the Amazon has a really important role in understanding the dynamics of access and utilization of the Biome. The Amazon Institute of People and the Environment (IMAZON), had been conducting this procedure in a manual way, making this precise process, longstading. With that in mind, this work propose a new way of making this mapping, using artificial intelligence and remote sensing technologies for accelerate the detecting of roads, making possible to tracking constantly activities in the Amazon. The model of neural net created to accomplish this task was made using a modified U-Net and using Google’s training and prediction services. The model was tested with five locations inside state of Pará, all of those with 1200 km² of area, and it produced promising results, which indicate the capacity of the network de make predictions over satellites images and identify the existence of roads, being capable of detect different formations - Dendritic, geometric and “Fishbone”. Besides that, another test to compare results between two types of images with different resolutions was conducted, showing improvement with the rising of the resolution, when made with the right input conditions. At last, this work accomplished its objective, presenting a new method to map unofficial roads in the Amazon, this being faster, less expensive and capable of keep up with the dynamic of the region.