Development of accurate classification of heavenly bodies using novel machine learning techniques

Abstract The heavenly bodies are objects that swim in the outer space. classification of these is a challenging task for astronomers. This article presents novel methodology enables an efficient and accurate cosmic (3 classes) based on evolutionary optimization classifiers. research collected data from Sloan Digital Sky Survey database. In this work, we proposing to develop machine learning model classify stellar spectra stars, quasars galaxies. First, input normalized then subjected principal component analysis reduce dimensionality. Then, genetic algorithm implemented which helps find optimal parameters We have used 21 classifiers robust with fivefold cross-validation strategy. Our developed has achieved improvement accuracy using nineteen out twenty-one models. obtained highest 99.16%, precision 98.78%, recall 98.08% F1-score 98.32% system voting classifier. prototype can help astronomers make sky. Proposed be other areas where many classes required.