K+ Means : An Enhancement Over K-Means Clustering Algorithm

TL;DR

The paper introduces K+ Means, an improved clustering algorithm that addresses the challenge of determining the optimal number of clusters in K-means, enhancing its effectiveness.

Contribution

It proposes K+ Means, a novel enhancement over K-Means, specifically designed to better handle the selection of the number of clusters.

Findings

K+ Means improves clustering accuracy.

It simplifies the process of choosing K.

Enhanced performance over traditional K-Means.

Abstract

K-means (MacQueen, 1967) [1] is one of the simplest unsupervised learning algorithms that solve the well-known clustering problem. The procedure follows a simple and easy way to classify a given data set to a predefined, say K number of clusters. Determination of K is a difficult job and it is not known that which value of K can partition the objects as per our intuition. To overcome this problem we proposed K+ Means algorithm. This algorithm is an enhancement over K-Means algorithm.