Abstract
Various clustering algorithms CA have been reported in literature to group data into clusters in diverse domains Literature further reported that these CAs work satisfactorily either on pure numerical data or on pure categorical data and perform poorly on mixed numerical and categorical data Clustering is the process of creating distribution patterns and obtaining intrinsic correlations in large datasets by arranging the data into similarity classes The present work pertains to reviewing the available research papers on clustering spatial data In a web perspective a detailed inspection of grouped patterns and their belonging to well known characters will be very useful for evolution of clusters The review work is split into spatial data mining clustering on spatial data sets and extended linked clustering This review work will enable the researchers to make an in depth study of the till date research work on above areas and will pave way for developing extended linked clustering algorithms with a view to find number of clusters on mixed datasets to produce results for several datasets This work is likely to assist in deciding which clustering solution to use to obtain a coherent data solution for a particular character experiment Further it could be used as an optimal tool to guide the clustering process towards better and character interpretable meaningful solutions The major contribution of present work is to present an in depth literature review of research in the areas of Spatial data mining clustering on spatial data sets and extended linked clustering with a view to assist researchers to develop optimum extended linked clustering and to develop optimum extended linked clustering algorithms for clustering process towards better and character interpretable meaningful solutionsThis work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2018 Authors and Global Journals Private Limited