SDSS-DR12 Bulk Stellar Spectral Classification: Artificial Neural Networks Approach

TL;DR

This paper investigates the use of neural networks and clustering algorithms to automate the classification of large stellar spectral datasets, aiming to improve efficiency and accuracy in astrophysical data analysis.

Contribution

It introduces an approach combining PNN, SVM, and Kmeans clustering for stellar spectral classification, offering a novel application of these methods in astrophysics.

Findings

PNN and SVM achieve high classification accuracy

Kmeans effectively groups similar spectra

Method improves automation in spectral analysis

Abstract

This paper explores the application of Probabilistic Neural Network (PNN), Support Vector Machine (SVM) and Kmeans clustering as tools for automated classification of massive stellar spectra.