Abstract—In order to further improve the computing efficiency of the KNN algorithm in a cluster environment, an improved parallelization algorithm based on the sequential MapReduce framework was proposed. Two MapReduce workflows were defined in sequence. The first workflow took training data as input to parallelize the process of calculating Euclidean distance; the second workflow took the output of the calculation process as input to parallelize the process of counting categories. The Experiments have verified that in a cluster environment, compared with a single MapReduce operation process, the sequential improvement accelerated the operation process of counting categories and improved the efficiency of the algorithm.
Index Terms—KNN, MapReduce, parallelization.
Yaoshun Li and Lizhi Liu are with School of Artificial Intelligence, School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China (e-mail: liyaoshuncn@foxmail.com).
[PDF]
Cite:Yaoshun Li and Lizhi Liu, "Improvement of Parallelization of KNN Algorithm Based on Sequential MapReduce," International Journal of Computer Theory and Engineering vol. 13, no. 2, pp. 56-60, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
