Track:
All Papers
Downloads:
Abstract:
In order to understand the process of formation and evolution of a galaxy, it is very important to identify the ages of stellar populations that make it up. The main contribution of this work is an efficient machine learning method, insensitive to emission lines and robust in the presence of noise, to determine the age of stellar populations in observational galactic spectra. It is a novel method for constructing ensembles where the decision in the prediction is done subdividing the data and organizing them in a tree structure. Experimental results show that our method yields a better accuracy than the traditional ensembles