Seybold Report ISSN: 1533-9211
S Archana1, Dr. Neeraj Sharma2, Dr. Pradosh chandra Patnaik3
1Research Scholar, Dept. of Computer Science and Engineering
Sri Satya Sai University of Technology and Medical Sciences,
Sehore Bhopal-Indore Road, Madhya Pradesh, India.
2Research Guide, Dept. of Computer Science and Engineering
Sri Satya Sai University of Technology and Medical Sciences,
Sehore Bhopal-Indore Road, Madhya Pradesh, India.
3Research Co-Guide, Professor & Principal . Dept. of Computer Science and Engineering
Aurora’s PG College (MCA) Hyderabad
Vol 17, No 10 ( 2022 ) | DOI: 10.5281/zenodo.7259992 | Licensing: CC 4.0 | Pg no:2048-2058 | Published on: 28-10-2022
Abstract
Clustering methods are particularly well-suited for identifying classes in spatial databases. However, when applied to large spatial datasets, the following needs for clustering algorithms become apparent: minimal domain knowledge is required to calculate the input parameters, clusters of any shape can be discovered, and huge databases demand high efficiency. The well-known clustering methods are incapable of meeting all of these requirements. Clustering is the process of grouping similar data from a population data set so that data points belonging to the same group have a higher degree of similarity than data points belonging to other groups. Data clustering enables academics to reduce the dimension of complex problems, create spam filters, detect fraudulent or illegal behaviour, analyse documents, classify network traffic, and aid in marketing or sales analysis. The data is compared to the numerous clusters that exist. The cluster with the greatest degree of proximity is picked to store the data. By utilising this algorithm, we can decrease access time and make data retrieval easier. Additionally, an iterative process is used to create such clusters within the data node itself, facilitating data access via parallelization.
Keywords:
Clustering Algorithm, Data clustering, Spatial database.