Research Article Open Access

An Efficient Approach for Computing Silhouette Coefficients

Moh'd B. Al- Zoubi1 and Mohammad al Rawi1
  • 1 ,
Journal of Computer Science
Volume 4 No. 3, 2008, 252-255

DOI: https://doi.org/10.3844/jcssp.2008.252.255

Published On: 31 March 2008

How to Cite: Al- Zoubi, M. B. & al Rawi, M. (2008). An Efficient Approach for Computing Silhouette Coefficients. Journal of Computer Science, 4(3), 252-255. https://doi.org/10.3844/jcssp.2008.252.255

Abstract

One popular approach for finding the best number of clusters (K) in a data set is through computing the silhouette coefficients. The silhouette coefficients for different values of K, are first found and then the maximum value of these coefficients is chosen. However, computing the silhouette coefficient for different Ks is a very time consuming process. This is due to the amount of CPU time spent on distance calculations. A proposed approach to compute the silhouette coefficient quickly had been presented. The approach was based on decreasing the number of addition operations when computing distances. The results were efficient and more than 50% of the CPU time was achieved when applied to different data sets.

Download

Keywords

  • Silhouette coefficients
  • clustering
  • data mining
  • pattern recognition