Analysis & comparison of neural network training algorithms for the joint time-frequency analysis

Authors:
Jamil Ahmad;Imran Shafi;Syed Ismail Shah;Faisal M. Kashif
Affiliations:
Iqra University Islamabad Campus, Islamabad, Pakistan;Centre for Advance Studies in Engineering, Islamabad, Pakistan;Iqra University Islamabad Campus, Islamabad, Pakistan;Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA
Venue:
AIA'06 Proceedings of the 24th IASTED international conference on Artificial intelligence and applications
Year:
2006

Citing 7
Cited 1

Entropy and information theory

Entropy and information theory
Time-frequency analysis: theory and applications

Time-frequency analysis: theory and applications
Artificial Neural Networks: A Tutorial

Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Neural network design

Neural network design
Weighted least squares implementation of Cohen-Posch time-frequencydistributions

IEEE Transactions on Signal Processing
Highly concentrated time-frequency distributions: pseudo quantumsignal representation

IEEE Transactions on Signal Processing
Generalized transfer function estimation using evolutionaryspectral deblurring

IEEE Transactions on Signal Processing

Techniques to obtain good resolution and concentrated time-frequency distributions: a review

EURASIP Journal on Advances in Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.