Document Classification Using KNN on GPU
Department of Computer Engineering, Vishwakarma Institute Of Engineering, Pune, Maharashtra, India
International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), Volume 3 Issue 8, 2014
@article{lade2014document,
title={Document Classification Using KNN on GPU},
author={Lade, SG and Vyawahare, Nikhil},
year={2014}
}
Real-time and archrival data documents are increases as fast as or faster than computing power now a days. Document classification using k-nn classification algorithm takes more time in searching nearer neighbors in large training dataset, it include large number of computations. The time for classification increases in proportion to the number of documents. Therefore it is necessary to find alternative for implementation of KNN.The Graphics processing unit consists of multi-core processors and they can perform computations in parallel, in small amount of time. This paper describes implementation of parallel k-nn algorithm for document classification on NVIDIA graphics processors.
September 8, 2014 by hgpu
