摘要
针对我们在第22届全国数据库学术会议中提出的基于MPI的改进小波聚类算法,利用消息传递MPI机制在曙光TC1700上实现了并行聚类。对编程涉及到的主要问题,寻找和标记网格连通区域进行了重点说明,并对程序实现使用的技巧给出了解释。最后对两组数据分别在5节点和9节点情况下聚类结果进行了比较,实验结果表明该算法是高效并且可行的。
A MPI-based parallel wavecluster algorithm was used to achieve parallel clustering by message-passing model on TC1700. The main problem involved in programming, finding and labling the connected components was explained, especially on the skill of programme making. The experiment results on two data set by 5 nodes and 9 nodes respectively show that our algorithm is efficient and effective.
出处
《计算机应用》
CSCD
北大核心
2006年第3期645-646,654,共3页
journal of Computer Applications