Active galactic nucleus selection in the AKARI NEP-Deep field with the fuzzy support vector machine algorithm
The aim of this work is to create a new catalog of reliable active galactic nucleus (AGN) candidates selected from the AKARI NEP-Deep field. Selection of the AGN candidates was done by applying a fuzzy support vector machine algorithm, which allows the incorporation of measurement uncertainties into the classification process. The training dataset was based on the spectroscopic data available for selected objects in the NEP-Deep and NEP-Wide fields. The generalization sample was based on the AKARI NEP-Deep field data, including objects without optical counterparts and making use of the infrared information only. A high quality catalog of 275 previously unclassified AGN candidates was prepared.