IMPLEMENTATION OF PARALLEL K-MEANS ALGORITHM FOR DIGIT CLASSIFICATION USING OPENMP AND MPI LIBRARIES
DOI:
https://doi.org/10.24867/25BE26TanovicKeywords:
Parallel algorithms, K-means algorithm, OpenMP, MPI, Digit ClassificationAbstract
This paper presents the development of the parallel k-means algorithm for digit classification. The basic k-means clustering algorithm is described, as well as its adaptation to the image set classification algorithm. The possibilities of parallelizing the algorithm were analyzed, and different versions of the parallel k-means algorithm were implemented using OpenMP and MPI libraries.
References
1] J. Wu, "Cluster Analysis and K-means Clustering: An Introduction. U: Advances in K-means Clustering." Springer Theses. Springer, Berlin, Heidelberg, 2012. doi: 10.1007/978-3-642-29807-3_1.
[2] L. Deng, "The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]," in IEEE Signal Processing Magazine, vol. 29, no. 6, strane 141-142, Nov. 2012, doi: 10.1109/MSP.2012.2211477.
[3] https://610yilingliu.github.io/2020/07/15/ScheduleinOpenMP/ posećeno septembar 2023.
[2] L. Deng, "The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]," in IEEE Signal Processing Magazine, vol. 29, no. 6, strane 141-142, Nov. 2012, doi: 10.1109/MSP.2012.2211477.
[3] https://610yilingliu.github.io/2020/07/15/ScheduleinOpenMP/ posećeno septembar 2023.
Downloads
Published
2023-12-06
Issue
Section
Electrotechnical and Computer Engineering
