Engenharias

Permanent URI for this community

https://ri.ucsal.br/handle/123456730/304

Browse

Browsing Engenharias by Subject "Aprendizado de máquina"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    e-Coach: um sistema de recomendação de equipes e personagens de league of legends utilizando redes neurais multicamadas
    (Universidade Católica do Salvador, 2019-06-18) Gonçalves, Danilo Silva; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Reis, Marcelo Indio dos; lattes.cnpq.br; Aquino, Pamela Arielle Brito de; lattes.cnpq.br
    The mode of electronic sports has been increasingly present in society, crowding stadiums in different parts of the world and conquering more and more supporters by where their events take place. Between investment and millionaire awards, a career as a cyber athlete has become a goal of young people in the gamer community, as well as encouraging other companies in the area. In this sense, this study demonstrates the implementation of an algorithm applying Multi Layer Perceptron networks, using as a database the results of ranked matches of League of Legends. In addition, it explains the execution of experiments with players in real matches using the algorithm and comparing them to matches without using the algorithm. Thus, making possible the realization of the prediction of which team and characters that best fit for the match in obtaining victory.
  • No Thumbnail Available
    Item
    Tipificação de ocorrências policiais utilizando machine learning
    (Universidade Católica do Salvador, 2019-06-18) Amorim, Matheus da Silva; Pereira, Juan Ribeiro Silva; Reis, Marcelo Indio dos; lattes.cnpq.br; Reis, Marcelo Indio dos; lattes.cnpq.br; Melo, Osvaldo Requião; lattes.cnpq.br; Aquino, Pamela Arielle Brito de; lattes.cnpq.br
    Public safety is one of the main pillars for society that directly influence the citizens quality of life. Lately this area has been receiving a great focus on the investment issue, as Ballesteros (2014) says his article, much of this value has been destined to process automation. In this context, technology enters to support various routine activities, making them more efficient through better management of their resources. With that, it was suggested in this assignment the use of machine learning algorithms, to automatically typify police occurrences. It was used a base of data with police records and from it some samples were taken for validation. For this tests were selected the algorithms C4.5, CART, KNN, SVM, Rede Neural, Ripper and Random Forest. The results gotten, indicated that the C4.5 and the Ripper had the best accuracy, becoming until 99% in some tests. In a test, the application of the coefficient of correlation of Matthews and of F1 score, reached 0.89 and 0.94 in that order.