@inproceedings{c7618231e93d457799c35814ea76c53c,
title = "Parallel outlier detection using KD-tree based on MapReduce",
abstract = "Distributed and Parallel algorithms have attracted a vast amount of interest and research in recent decades, to handle large-scale data set in real-world applications. In this paper, we focus on a parallel implementation of KD-Tree based outlier detection method to deal with large-scale data set. As one of the state-of-the-art outlier detection methods, KD-Tree based has been approved to be an effective algorithm. However, it still cannot process large-scale data set efficiently due to its serial implementation. Based on the current and powerful parallel programming framework - MapReduce, we propose to implement the parallel KD-Tree based outlier detection algorithm (e.g., PKDTree for short). Experimental results demonstrate the efficiency of PKDTree according to the evaluation criterions of scaleup, speedup and sizeup.",
keywords = "Data mining, KDTree, MapReduce, Parallel Outlier Detection",
author = "Qing He and Yunlong Ma and Qun Wang and Fuzhen Zhuang and Zhongzhi Shi",
year = "2011",
doi = "10.1109/CloudCom.2011.20",
language = "英语",
isbn = "9780769546223",
series = "Proceedings - 2011 3rd IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2011",
publisher = "IEEE Computer Society",
pages = "75--80",
booktitle = "Proceedings - 2011 3rd IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2011",
address = "美国",
note = "3rd IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2011 ; Conference date: 29-11-2011 Through 01-12-2011",
}