Neural Networks for Spectral Analysis of Unevenly Sampled Data
In this paper we present a neural network based estimator system which performs well the frequency extraction from unevenly sampled signals. 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 overfrtting.
The experimental results are obtained comparing our methodology with the others known in literature.
KeywordsLight Curve Stop Criterion Spectral Estimator Overfitting Problem Neural Network Weight
Unable to display preview. Download preview PDF.
- S. L. Marple, Digital spectral analysis with applications, Prentice-Hall, Englewood Cliffs, N.J., 1987.Google Scholar
- A. V. Oppenhaim, R. W. Schafer, Digital Signal Processing, Prentince-Hall, 1965.Google Scholar
- M. Rasile, L. Milano, R. Tagliaferri, G. Longo, Periodicity Analysis of Unvenly Spaced Data by Means of Neural Networks, in Neural Nets WIRN Vietri 97, M. Marinaro and R. Tagliaferri Editors, Springer Verlag, pag.201–212, 1997.Google Scholar
- R. Roy, T. Kailath, ESPRIT-Estimation of Signal Parameters via Rotational Invariance Tecniques, in F.A. Grünbaum, J. W. Helton and P. Khargonear Editors, Signal Processing Part II: Control Theory and Applications, Springer Verlag, New York, pag.369–411, 1990.Google Scholar
- R. Tagliaferri, A. Ciaramella, L. Milano, F. Barone, G. Longo, Spectral Analysis of Stellar Light Curves by Means of Neural Networks, accepted for publication, Astronomy & Astrophysics Supplement Series, vol.137, June, 1999.Google Scholar