01. Universidade Federal Rural de Pernambuco - UFRPE (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/1
Navegar
2 resultados
Resultados da Pesquisa
Item Explainable Artificial Intelligence - uma análise dos trade-offs entre desempenho e explicabilidade(2023-08-18) Assis, André Carlos Santos de; Andrade, Ermeson Carneiro de; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/2466077615273972; http://lattes.cnpq.br/3963132175829207Explainability is essential for users to efficiently understand, trust, and manage computer systems that use artificial intelligence. Thus, as well as assertiveness, understanding how the decision-making process of the models occurred is fundamental. While there are studies that focus on the explainability of artificial intelligence algorithms, it is important to highlight that, as far as we know, none of them have comprehensively analyzed the trade-offs between performance and explainability. In this sense, this research aims to fill this gap by investigating both transparent algorithms, such as Decision Tree and Logistic Regression, and opaque algorithms, such as Random Forest and Support Vector Machine, in order to evaluate the trade-offs between performance and explainability. The results reveal that opaque algorithms have a low explanability and do not perform well regarding response time due to their complexity, but are more assertive. On the other hand, transparent algorithms have a more effective explainability and better performance regarding response time, but in our experiments, we observed that accuracy obtained was lower than the accuracy of opaque models.Item Um sistema de recomendações de eventos culturais com áudio-descrição(2018) Souza Filho, Robson Ugo Ferreira; Medeiros, Victor Wanderley Costa de; Falcão, Taciana Pontual da Rocha; http://lattes.cnpq.br/5706959249737319; http://lattes.cnpq.br/7159595141911505Around one billion people in the world live with some kind of disability, while almost 24% of the Brazilian population has declared some kind of disability in the 2010 CENSUS. Therefore, the increasingly constant presence of people with visual impairment in cutural spaces has increased and is also due to the presence of communicational accessibility resources. The technological advance has made the disposition of such resources much easier and closer, increasing audience’s autonomy. Based on this argument, this work aims to present the planning and development of an audio-description cultural event recommendation system for blind people using mobile devices, increasing the independence and capacity of the natural indication process to human relationships through collaborative filtering item-based and content-based algorithms. We generated a potential database of these kinds of events, a study about the proposed algorithms and an application usability experiment. The absence of statistical evaluation for the maden evaluations was discovered, since the users’ approach in selecting notes for the events is personal, also resulting from the non-existent consistency of its data.