Decision table for classifying point sources based on FIRST and 2MASS databases

TL;DR

This paper develops a decision table-based classification method for celestial objects using multiwavelength data from FIRST and 2MASS, achieving over 95.9% accuracy and aiding large survey projects.

Contribution

It introduces a feature selection and decision table approach for classifying stars and quasars, demonstrating high accuracy and robustness.

Findings

Classification accuracy exceeds 95.9%

Feature selection improves effectiveness and efficiency

Decision table effectively discriminates celestial objects

Abstract

With the availability of multiwavelength, multiscale and multiepoch astronomical catalogues, the number of features to describe astronomical objects has increases. The better features we select to classify objects, the higher the classification accuracy is. In this paper, we have used data sets of stars and quasars from near infrared band and radio band. Then best-first search method was applied to select features. For the data with selected features, the algorithm of decision table was implemented. The classification accuracy is more than 95.9%. As a result, the feature selection method improves the effectiveness and efficiency of the classification method. Moreover the result shows that decision table is robust and effective for discrimination of celestial objects and used for preselecting quasar candidates for large survey projects.