Title :
Hopfield neural network for AR spectral estimator
Author_Institution :
Dept. of Electr. Eng., Tennessee Technol. Univ., Cookeville, TN, USA
Abstract :
An autoregressive (AR) spectrum estimator which uses the Hopfield neural network (HNN) is introduced. The HNN is designed to minimize the mean squared error between a subject signal and the assumed AR model of that signal. The output of the HNN consists of the AR coefficients, so that the spectrum of the signal can be directly obtained in terms of the AR coefficients and the sampling interval. A symmetric soft-limiter-type neuron was selected for the HNN. Simulation results are provided
Keywords :
neural nets; signal processing; spectral analysis; AR spectral estimator; Hopfield neural network; mean squared error; symmetric soft-limiter-type neuron; Direction of arrival estimation; Entropy; Hopfield neural networks; Neural networks; Neurons; Radar applications; Radar signal processing; Sampling methods; Signal design; Sonar applications;
Conference_Titel :
Southeastcon '90. Proceedings., IEEE
Conference_Location :
New Orleans, LA
DOI :
10.1109/SECON.1990.117878
