Clustering Analysis of Kepler Exoplanet Data Using the Simple K-Means Algorithm

Abstract

The discovery of exoplanets has generated a massive volume of astronomical data, requiring efficient analytical methods to detect hidden patterns and features. One approach that can be implemented is clustering using data mining techniques. This study aims to examine the clustering process of exoplanet data obtained from the Kepler Telescope using the Simple K-Means algorithm. The data analyzed in this research were sourced from the Kepler exoplanet dataset and processed using the WEKA software. The research stages included data selection, preprocessing, clustering implementation, and evaluation of clustering results. The clustering process was carried out using the Simple K-Means algorithm with several predefined clusters to identify similarities in exoplanet characteristics. The results indicate that the algorithm can effectively group exoplanet data based on similar characteristics and produce satisfactory cluster distributions with a minimal error rate. In addition, the clustering visualization successfully illustrated the distribution patterns of exoplanet data within each cluster. These findings suggest that Simple K-Means can be efficiently applied for exoplanet data exploration and support the process of astronomical data analysis. This study is expected to contribute to the development of data mining applications in the field of astronomy, particularly in exoplanet data analysis.