Mining Intelligent Spatial Clustering Patterns: A Comparative Analysis of Different Approaches

Abstract

Spatial data is a collection of information about the geospatial location and its events or characteristics. These spatial data are collected from the various positioning techniques viz. Global Positioning System (GPS), remote sensing, mobile devices, etc. A large amount of easily available spatial data drives the need to effectively uncover useful and interesting patterns using machine learning algorithms like Clustering. Clustering is a technique to group geospatial data possessing similar properties, characteristics to retrieve events or patterns of significance. This paper presents a comparative analysis of various algorithms on clustering and extensions of methods, conception, and their applications in various domains. The comparative analysis revels that the Density Peak Clustering algorithm has high accuracy on the IRIS dataset Finally, we present the research opportunities in spatial data clustering in the future enhancement section.