HNS – a hybrid neural system and its use for the classification of stars

Abstract

A novel hybrid neural approach for a fully automated spectral and luminosity classification of stars is presented. The hybrid neural system (HNS) integrates a neural classifier and a semantic network used for similarity based reasoning and conceptual knowledge representation, respectively. For neural classification the HNS currently uses data based on the uvby photometric system. The semantic net is designed in accordance to the MK classification of stars. In this paper, the structure, functionality and application of the hybrid system are presented. The demonstrated functional capabilities, performance and results of stellar classification of the HNS show significant improvements compared to conventional astronomical techniques. After knowledge acquisition is once completed, the system classifies stellar objects very fast, reliable and without any need for pre-classification of them. In particular the HNS is also able to compare classes of stars without forcing the user to give any raw input data and special knowledge about relations between classes of stars. Moreover, this new hybrid approach offers a variety of applications in other areas.