@inproceedings{7dfa745add784eaea155985fff326a1b,

title = "DVT-PKM: An improved GPU based parallel K-means algorithm",

abstract = "K-Means clustering algorithm is a typical partition-based clustering algorithm. Its two major disadvantages lie in the facts that the algorithm is sensitive to initial cluster centers and the outliers exert significant influence on the clustering results. In addition, K-Means algorithm traverses and computes all the data multiple times. Thus, the algorithm is not efficient when dealing with large data sets. In order to overcome the above limitations, this paper proposes to exclude the outliers using the minimum number of points in the d-dimensional hypersphere area. Then k cluster centers can be obtained by adjusting the threshold making use of density idea. Finally, K-Means algorithm will be integrated with Compute Unified Device Architecture (CUDA). The time efficiency is improved considerably through taking advantage of computing power of Graphic Processing Unit (GPU). We use the ratio of distance between classes to distance within classes and speedup as the evaluation criteria. The experiments indicate that the proposed algorithm significantly improves the stability and running efficiency of K-Means algorithm.",

keywords = "Graphic Processing Unit, K-Means, density",

author = "Bo Yan and Ye Zhang and Zijiang Yang and Hongyi Su and Hong Zheng",

year = "2014",

doi = "10.1007/978-3-319-09339-0_60",

language = "English",

isbn = "9783319093383",

series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",

publisher = "Springer Verlag",

pages = "591--601",

booktitle = "Intelligent Computing Methodologies - 10th International Conference, ICIC 2014, Proceedings",

address = "Germany",

note = "10th International Conference on Intelligent Computing, ICIC 2014 ; Conference date: 03-08-2014 Through 06-08-2014",

}