Hybrid Neural Networks for Frequency Estimation of Unevenly Sampled Data

In this paper we present a hybrid system composed by a neural network based estimator system and genetic algorithms. It uses an unsupervised Hebbian nonlinear neural algorithm to extract the principal components which, in turn, are used by the MUSIC frequency estimator algorithm to extract the frequencies. We generalize this method to avoid an interpolation preprocessing step and to improve the performance by using a new stop criterion to avoid overfitting. Furthermore, genetic algorithms are used to optimize the neural net weight initialization. The experimental results are obtained comparing our methodology with the others known in literature on a Cepheid star light curve.