Analysis & Comparison of Neural Network Training Algorithms for the Joint Time-Frequency Analysis

In this paper we present a comparison of Neural Network Training Algorithms for obtaining a Time Frequency Distribution (TFD) of a signal whose frequency components vary with time. The method employs various algorithms used in NNs which are trained by using the spectrograms of several training signals as input and TFDs that are highly concentrated along the instantaneous frequencies (IFs) of the individual components present in the signal as targets. The trained neural networks are then presented with the spectrogram of unknown signals. We compute the entropy as a measure of the result obtained and carry out error and time analysis to compare the performance of algorithms used.

[1]  Ljubisa Stankovic,et al.  Highly concentrated time-frequency distributions: pseudo quantum signal representation , 1997, IEEE Trans. Signal Process..

[2]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[3]  Aydin Akan,et al.  Discrete evolutionary transform for time-frequency signal analysis , 2000, J. Frankl. Inst..

[4]  Luis F. Chaparro,et al.  Generalized transfer function estimation using evolutionary spectral deblurring , 1999, IEEE Trans. Signal Process..

[5]  Martin T. Hagan,et al.  Neural network design , 1995 .

[6]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[7]  Min Su,et al.  Deblurring images using projection pursuit learning network , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[8]  R. Gray.  Entropy and Information Theory , 1990, Springer New York.

[9]  Giuseppe Buja,et al.  Neural network technique for the joint time-frequency analysis of distorted signal , 2003, IEEE Trans. Ind. Electron..

[10]  Patrick J. Loughlin,et al.  Weighted least squares implementation of Cohen-Posch time-frequency distributions , 1998, IEEE Trans. Signal Process..