Exploring the Viability of Fisher Discriminants in Galaxy Morphology Classification

TL;DR

This study evaluates the effectiveness of Fisher discriminants, a simple classification algorithm, in galaxy morphology classification, demonstrating comparable or superior accuracy to more complex methods using SDSS data.

Contribution

It demonstrates that Fisher discriminants, combined with data preprocessing, can effectively classify galaxy shapes, offering a simpler alternative to complex algorithms.

Findings

Fisher discriminant with uniformisation achieved 93.10% accuracy.

Fisher discriminant outperformed ANN, BDT, and kNN in accuracy.

Simple Fisher discriminants can be viable for galaxy classification tasks.

Abstract

One of the major challenges in astronomy involves accurately classifying galaxies, particularly distinguishing between different galaxy types. While many complex algorithms have shown strong performance in classification tasks, their complexity often results in longer processing times and increased difficulty in understanding. This study addresses this issue by exploring the viability of Fisher discriminants, a much simpler algorithm, in performing galaxy morphology classification. We tested four machine learning algorithms: the Fisher discriminant, Artificial Neural Networks (ANNs), Boosted Decision Trees (BDTs), and k-Nearest Neighbours (kNNs) to classify galaxies by the shape of their central bulges. Using data from the Sloan Digital Sky Survey (SDSS), we utilised five pre-processing transformations: normalisation, decorrelation, principal component analysis (PCA), uniformisation, and Gaussianisation, and classified the shape of central bulge into either rounded or no-bulge, based on the Galaxy Zoo Decision Tree. When compared to the Galaxy Zoo 2 (GZ2) labels, the Fisher discriminant with uniformisation obtained the highest accuracy score of 0.9310, outperforming ANN, BDT, and kNN by 1.93%, 0.42%, and 3.08%, respectively.