Analysis of Time Series with Artificial Neural Networks

This paper presents the study of time series in gravitational lensing to solve the time delay problem in astrophysics. The time series are irregularly sampled and noisy. There are several methods to estimate the time delay between this kind of time series, and this paper proposes a new method based on artificial neural networks, in particular, General Regression Neural Networks (GRNN), which is based on Radial Basis Function (RBF) networks. We also compare other typical artificial neural network architectures, where the learning time of GRNN is better. We analyze artificial data used in the literature to compare the performance of the new method against state-of-the-art methods. Some statistics are presented to study the significance of results.

[1]  Salvador Torra Porras.  Siniestralidad en seguros de consumo anual de las entidades de previsión social, La. Perspectiva probabilística y econométrica. Propuesta de un modelo econométrico neuronal para Cataluña. , 2004 .

[2]  J. Carlos,et al.  Estimating time delays between irregularly sampled time series , 2007 .

[3]  Lakhmi C. Jain,et al.  Radial Basis Function Networks 2: New Advances in Design , 2001 .

[4]  Bernard F. Burke,et al.  The radio time delay in the double quasar 0957 + 561 , 1992 .

[5]  Peter Tiño,et al.  A Kernel-Based Approach to Estimating Phase Shifts Between Irregularly Sampled Time Series: An Application to Gravitational Lenses , 2006, ECML.

[6]  Markus Harva,et al.  Bayesian Estimation of Time Delays Between Unevenly Sampled Signals , 2008, 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing.

[7]  William H. Press,et al.  The Time Delay of Gravitational Lens 0957+561. I. Methodology and Analysis of Optical Photometric Data , 1992 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Y. Mellier,et al.  Gravitational Lensing , 1990 .

[10]  J. Hjorth,et al.  ESTIMATION OF MULTIPLE TIME DELAYS IN COMPLEX GRAVITATIONAL LENS SYSTEMS , 1998 .

[11]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[12]  Georg Dorffner,et al.  Neural Networks for Time Series Processing , 1996 .

[13]  O. Wucknitz.  Gravitational Lensing , 2007, Large-Scale Peculiar Motions.

[14]  Raymond J. Spiteri,et al.  Inverting Gravitational Lenses , 2002, SIAM Rev..

[15]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[16]  Douglas John Percival.  Spectral representation of irregularly sampled radar image sequences , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.