A Multi-Layer Perceptron (MLP) Neural Networks for Stellar Classification: A Review of Methods and Results

Abstract

The remarkable capacity of artificial intelligence (AI) to analyze enormous quantities of information and create precise forecasts has led to its growing prominence in the field of scientific Astrophysics. Stellar categorization is the process by which stars are sorted according to the characteristics revealed by their spectra. To analyze the star's electromagnetic radiation, a diffraction or prism screen separates it into a spectrum with an assortment of hues and spectral lines used to categorize the star. Star wavelengths are an extremely important piece of data for space-based photography studies. Employing data from over 100,000 cases and a variety of AI models, this study demonstrates how to categorize stellar properties as either a Galaxy or a Star. This paper used the multi-layer perceptron (MLP) neural network (NN) for stellar classification. The MLP is applied in 18 features. This paper showed the correlation between these features. This paper achieved 97% accuracy from the MLP model. This study compared various optimizers to show the best optimizer. The Adagrad optimizer is the best optimizer due to getting the highest validation accuracy.