Classification of Kepler exoplanet searching from galaxy using machine learning model
Computer Science and Engineering, Centurion University of Technology and Management, Odisha, India.
Review Article
World Journal of Advanced Research and Reviews, 2024, 21(01), 227-230
Article DOI: 10.30574/wjarr.2024.21.1.0012
Publication history:
Received on 22 November 2023; revised on 01 January 2024; accepted on 04 January 2024
Abstract:
The Kepler exoplanet mission was designed specifically to search the Milky Way galaxy for numerous small planets the size of Earth that are either in or close to the habitable zone. An exoplanet is a planet that orbits stars outside of our solar system. The dataset, which was gathered from the Kaggle website, has 50 columns and 9564 samples. The target variable in the dataset, KOI-disposition, comprises candidate, false positive and confirmed data. We discovered that 5000 samples out of 9564 samples were false positives; each confirmed sample had 2282 candidates. While there are many stars and planets in the Milky Way galaxy, we have only looked at a small number of them. In order to search for exoplanets beyond our stellar atmosphere, we have employed machine learning algorithms on stars and planets, such as decision trees, random forests, KNN classification, and Naive Bayes classification.
Keywords:
Kepler Exoplanets data; KNN; Random Forest; Decision Tree.
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0