Earticle

초록

영어

Affinity Propagation (AP) is a new clustering method to cluster data set efficiently. In this paper, a Distributed method of Local Affinity Propagation (DLAP) is proposed to solve hardware bottleneck and time-consuming problem. DLAP refines AP by reducing the calculating data scale in each iteration and keeps a high quality clustering result. The method is implemented on Apache Spark distributed computation framework. Depending on high iteration efficiency on Spark, the method has an impressive result in time complexity. Experiments are conducted on two-dimensional data to show that the time cost of LAP on single machine is better than the two methods, FSAP and FAP, meanwhile the result of DLAP on Spark is better than that on Hadoop.

목차

Abstract
 1. Introduction
 2. Related Work
  2.1. Affinity Propagation
  2.2. Dataset Scale Reduction
  2.3. Parallel Realization
 3. Distributed Local Affinity Propagation Method
  3.1. Local Dataset Reduction
  3.2. Parallel Realization on Spark
 4. Experiments
 5. Conclusions
 References

키워드

저자

• Wei Lu [ School of Software Engineering, Beijing Jiaotong University, Beijing, China ]
• Peng Cao [ School of Software Engineering, Beijing Jiaotong University, Beijing, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605