Clustering ICT Indicators of Bhutan using Two Level HSOM Algorithm

In this paper, a novel two level HSOM algorithm for clustering information and communication technology (ICT) indicators is presented. The purpose of this research study is to analyze the twenty districts ICT data of Bhutan using HSOM clustering algorithm. The HSOM possesses a two-level hybrid connectionist architecture that comprises (i) an agglomerative hierarchical clustering algorithm to create hierarchy of data in dendrogram from the principal component analysis(PCA) reduced data and (ii) an unsupervised neural network based Self-Organizing map classifier,which generates the final cluster output in single umatrix map. It is confirmed that HSOM obtains the effective output reflecting distribution state of input data. Ultimately we analyzed present scenario of ICT situation with clustering algorithm. ICT is one of the enabler of socio-economic developmental activities in Bhutan. Outcome from this research will help newly elected democratic government to achieve sustain able and equitable development in its 10^th five year plan (2008-2013).