A comprehensive study on k-means algorithms initialization techniques for wireless sensor network


The k-means initialization technique for a wireless sensor network is a newly emerging area for researchers. There are many constraints in designing the wireless sensor network. The primary constraint is energy consumption. Clustering is used for improving the lifetime of the system by reducing the power consumption. The most popular clustering technique is k-means algorithm but it exhibits local minima problem due to initial center selection. This paper provides the comprehensive survey of different initialization techniques such as Uniform Sampling, Random Sampling, k-means++ and Density based initialization. The above comparison has been made by taking the account of energy consumption and the lifetime of the wireless sensor network.

4 Figures and Tables

Showing 1-10 of 29 references

Ghayekhloo,“K-Means Clustering with a New Initialization Approach for Wind Power Forecasting,

  • M. Ghofrani, M. Rezende, R. Azimi
  • 2016
1 Excerpt

A novel approach for initializing the spherical K-means clustering algorithm

  • R. Duwairi, A. M. Rahmeh
  • 2015
1 Excerpt

Logic Technique in Digital Images using Edge Detection,

  • B. S. Jadon, N. Gupta, “Fuzzy
  • 2013

A clustering method based on K-Means algorithm

  • Li. Youguo, Wu. Haiyan
  • 2012
1 Excerpt