| Title |
An Efficient Data Partitioning Method based Cell Partitioning Parallel Hierarchical Agglomerative Clustering Using GPU |
| DOI |
https://doi.org/10.5573/ieie.2019.56.11.123 |
| Keywords |
Data partitioning ; Hierarchical agglomerative clustering ; Parallel clustering ; GPU ; CUDA ; |
| Abstract |
Today, interest in big data and data mining technologies is increasing to extract meaningful information from many data. Various researches on clustering methods for discovering highly related data among these techniques are actively conducted. Traditional clustering methods use a lot of memory and processing time for large amounts of data. This is because repetitive arithmetic operations are performed sequentially. In order to solve these problems, we have recently researched methods and propose a cell partitioning parallel hierarchical agglomerative clustering method that improves the traditional hierarchical agglomerative clustering and partially overlapping partitioning hierarchical agglomerative clustering method. Comparing the execution time of the three methods on the CPU and GPU, the proposed cell partitioning parallel hierarchical agglomerative clustering method on the CPU is up to 10 times faster than the traditional hierarchical agglomerative clustering method, and up to 2.5 times faster than the partially overlapping partitioning hierarchical agglomerative clustering method, and there were up to 6 times and 2 times speedups on the GPU, respectively. |