An effective multi-level synchronization clustering method based on a framework of “divide and collect” and SSynC algorithm

EasyChair Preprint no. 1438

Abstract

Facing big data, general clustering methods cannot process all data in main memory one time. In order to conquer this problem, this paper presents an effective Multi-Level Synchronization Clustering (MLSynC) method based on SSynC algorithm by using a framework of “divide and collect” and a linear weighted Vicsek model. MLSynC method has different process with SynC algorithm, ESynC algorithm, and SSynC algorithm. In this paper, we present two concrete implementations of MLSynC method, a two-level framework algorithm and a recursive algorithm. By the theoretic analysis, we find the time complexity of MLSynC method is less than SSynC algorithm. By some simulated experiments of some artificial data sets, eight UCI data sets, and three picture data sets, we observe that MLSynC method not only gets better local synchronization effect but also needs less iterative times and time cost than SynC algorithm. Moreover, we also observe that MLSynC method not only needs less time cost than ESynC algorithm and SSynC algorithm, but also almost gets the same local synchronization effect as ESynC algorithm and SSynC algorithm if the partition of the data set is proper. Further comparison experiments with some classical clustering algorithms demonstrate the clustering effect of MLSynC method.

Keyphrases: A linear weighted Vicsek model, Divide and collect, Kuramoto model, Near neighbor point set, Shrinking synchronization clustering

@Booklet{EasyChair:1438,
  author = {Xinquan Chen},
  title = {An effective multi-level synchronization clustering method based on a framework of “divide and collect” and SSynC algorithm},
  howpublished = {EasyChair Preprint no. 1438},

  year = {EasyChair, 2019}}