Open AccessAUMENTANDODESEMPENHO DEALGORITMOSDEMINERAÇÃODEDADOSUTILIZANDOAPLATAFORMACUDA
Author(s) -
Matheus Varela Ferreira,
Francisco Assis da Silva,
Leandro Luiz de Almeida,
Danillo Roberto Pereira
Publication year - 2018
Publication title -
colloquium exactarum
Language(s) - English
Resource type - Journals
ISSN - 2178-8332
DOI - 10.5747/ce.2018.v10.n1.e226
Subject(s) - cuda , computer science , conjunction (astronomy) , process (computing) , general purpose computing on graphics processing units , central processing unit , a priori and a posteriori , data processing , parallel computing , graphics , database , operating system , philosophy , physics , epistemology , astronomy
With the increasing need to make decisions in the short term, industry (pharmaceutical, petrochemical, aeronautics and etc.) has been seeking new ways to reduce the time of the data mining process to obtain knowledge. In recent years, many technological resources are being used to mitigate this need, an example is CUDA. CUDA is a platform that enables the use of GeForce GPUs in conjunction with CPUs for data processing, significantly reducing processing time. This work proposes to perform a comparative analysis of the processing time between two versions of some data mining algorithms (Apriori, AprioriAll, Naïve Bayes and K-Means), one running on CPU only and one on CPU in conjunction with GPU through platform CUDA. Through the experiments performed, it was observed that using the CUDA platform it is possible to obtain satisfactory results.