Mixture of Experts for Stellar Data Classification

In this paper, mixture of experts model is first applied to stellar data classification. In order to obtain input patterns of mixture of experts model, we present a feature extraction method for stellar data based on wavelet packet transformation. Then a mixture of experts model is built for classifying the feature vectors. A comparative study of different classification methods such as a single radial basis function neural network is given. Real world data experimental results show that the mixture of experts has a good generalization ability and the obtained correct classification rate is higher than that of using a single neural network.