Dynamic Euclidean K-Means Clustering Algorithm in Data Mining

Abstract

Data mining was the practice of processing data in order to derive interesting patterns as well as designs from the system used to analyze data. Grouping was the process of grouping artifacts even though that items in almost the same category are more identical than items in other classes. The existing system main drawbacks are not able to show clear logical information about the market analysis and cannot summarize the strength, weakness, opportunities and threats. Among these clustering is considered as a significant technique to capture the structure of data. Data mining adds to clustering is complicated to retrieve Wide databases with either a variety of different forms of attributes. This includes special specific clustering strategies with Euclidean K-Means grouping process. The power of k-means algorithm is due to its computational efficiency and the nature of ease at which it can be used. In this technique the threshold value is used to determine the information is the same category or even a new team is formed. Proposing an Euclidean K-means algorithm is a necessity. The squared Euclidean distance metric results of the suggested algorithm are tested in this journal experimental results. Distance metrics are used to build reliable features and functionality including grouping for data mining. The simulation process is carried out in MATLAB tool and outperforms the proposed results.