P-k-Means: k-Means Using Partition Based Cluster Initialization Method

7 Pages Posted: 6 Oct 2019

See all articles by Manoj Kumar Gupta

Manoj Kumar Gupta

Rukmini Devi Institute of Advanced Studies, Students; USIC&T, GGSIPU

Pravin Chandra

USIC&T, GGSIPU

Date Written: October 1, 2019

Abstract

The k-Means algorithm is extensively used in a number of data clustering applications. In basic k-means, initial cluster centroids are selected on random basis. As a result, every run of k-means leads to the formation of different clusters. Hence, accuracy and performance of k-means is susceptible to the selection of initial cluster centroids. Therefore, careful initialization of cluster centroids plays a major role on accuracy and performance of the k-means algorithm. In view of this, a new k-means using Partition based Cluster Initialization method called as ‘P-k-means’ is proposed in this paper. The experiment is carried out on six different datasets. The empirical results are compared using various external and internal clustering validation measures. The comparative results show that P-k-means is better than basic k-means.

Keywords: k-means; Clustering; Cluster Initialization; Partition based Cluster Initialization; P-k-means; Data Mining.

Suggested Citation

Gupta, Manoj Kumar and Chandra, Pravin, P-k-Means: k-Means Using Partition Based Cluster Initialization Method (October 1, 2019). Proceedings of International Conference on Advancements in Computing & Management (ICACM) 2019. Available at SSRN: https://ssrn.com/abstract=3462549 or http://dx.doi.org/10.2139/ssrn.3462549

Manoj Kumar Gupta (Contact Author)

Rukmini Devi Institute of Advanced Studies, Students ( email )

Delhi
India
9312635762 (Phone)
110085 (Fax)

HOME PAGE: http://rdias.ac.in

USIC&T, GGSIPU ( email )

Delhi
India
9312635762 (Phone)
110078 (Fax)

HOME PAGE: http://ipu.ac.in/usict/

Pravin Chandra

USIC&T, GGSIPU ( email )

Delhi
India

HOME PAGE: http://ipu.ac.in/usict/

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
54
Abstract Views
236
rank
403,219
PlumX Metrics