Effect of Distance Functions on K-Means Clustering Algorithm
Richa Loohach, Kanwal Garg · 2012
Clustering analysis is the most significant step in data mining. This paper discusses the k-means clustering algorithm and various distance functions used in k-means clustering algorithm such as Euclidean distance function and Manhattan distance function. Experimental results are shown to observe the effect of Manhattan distance function and Euclidean distance function on k-means clustering algorithm. These results also show that distance functions furthermore affect the size of clusters formed by the k-means clustering algorithm.