Efficiency and Effectiveness of Clustering Algorithms for High Dimensional Data
Smita Chormunge, Sudarson Jena · International Journal of Computer Applications · 2015
Clustering high dimensional data is challenging due to its dimensionality problem and it affects time complexity and accuracy of clustering methods.This paper presents the Fmeasure and Euclidean distance based performance efficiency and effectiveness of K-means and Agglomerative hierarchical clustering methods on Text and Microarray datasets by varying cluster values.Efficiency concerns about computational time required to build up dataset and effectiveness concerns about accuracy to cluster the data.Experimental results on different datasets demonstrate that Kmeans clustering algorithm is favourable in terms of effectiveness where as Agglomerative hierarchical clustering is efficient in time for text datasets used for empirical study.