Searching for previously unknown classes of objects in the AKARI-NEP Deep data with fuzzy logic SVM algorithm

TL;DR

This paper introduces a novel fuzzy SVM algorithm applied to AKARI NEP Deep data, successfully classifying MIR sources into stars, galaxies, and AGNs, including objects without optical counterparts, revealing new object classes.

Contribution

It presents the first application of fuzzy SVM in astronomy, improving classification by incorporating measurement errors and identifying previously unknown object classes.

Findings

Reliable catalogues of MIR sources classified into stars, galaxies, and AGNs.

Identification of objects with no optical counterparts, including AGB stars.

Demonstration of fuzzy SVM's effectiveness in astronomical classification.

Abstract

In this proceedings application of a fuzzy Support Vector Machine (FSVM) learning algorithm, to classify mid-infrared (MIR) sources from the AKARI NEP Deep field into three classes: stars, galaxies and AGNs, is presented. FSVM is an improved version of the classical SVM algorithm, incorporating measurement errors into the classification process; this is the first successful application of this algorithm in the astronomy. We created reliable catalogues of galaxies, stars and AGNs consisting of objects with MIR measurements, some of them with no optical counterparts. Some examples of identified objects are shown, among them O-rich and C-rich AGB stars.