基于数据预处理的并行分层聚类算法*

分层聚类技术在图像处理、入侵检测和生物信息学等方面有着极为重要的应用,是数据挖掘领域的研究热点之一。针对目前基于SIMD模型的并行分层聚类算法处理海量数据时效果不理想的问题,提出一种基于数据预处理的自适应并行分层聚类算法，在O((λn)2/p)的时间内对n个输入数据点进行聚类。其中1≤p≤n/log n,0.1≤λ≤0.3。将提出的算法与现有文献结论进行的性能对比分析表明，本算法明显改进了现有文献的研究结果。

Parallel hierarchical clustering algorithm based on preprocessed data

Hierarchial clustering technology plays a very important role in image processing, intrusion detection and bioinformatics applications, which is one of the most extensively studied branch in data mining. Presently the parallel hierarchical algorithms aren't very good at processing large data. To overcome this shortcoming, this paper proposed a new parallel algorithm based on preprocessed data. The proposed algorithms could cluster n objects with O(p) processors in O((λn)~2/p) time, where 1≤p≤n/log n,0.1≤λ≤0.3. Performance comparisons show that it is the first parallel hierarchical clustering algorithm without memory conflicts, and thus it is an improved result over the past researches.