Line Spectral Estimation Inspired by Quasi-Neural Network
- 16 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 70 (1053587X) , 5822-5832
Abstract
Different from a conventional artificial neural network (ANN) typically being used as a data-driven classifier, the “quasi-neural network” (Quasi-NN), with its inputs, outputs, and activation functions being artfully defined to have explicit physical meaning, is recently proposed in the literature as a modeling tool. In this paper, we show that the classic problem of line spectral estimation can be modeled by a Quasi-NN with its weights being the frequencies and the coefficients of the sinusoids to estimate. Owing to the layered structure the same as an ANN, the weights of the Quasi-NN can be optimized using the celebrated back-propagation (BP) algorithm initialized by the fast Fourier transform (FFT) based spectral estimation. The optimized weights are the maximum likelihood (ML) estimation of the line spectrum parameters. We also design a method of merging and pruning the hidden-layer nodes of the Quasi-NN for model-order selection, i.e., to estimate the number of sinusoids. Numerical simulations verify the effectiveness of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61771005)
This publication has 32 references indexed in Scilit:
- On Gridless Sparse Methods for Line Spectral Estimation From Complete and Incomplete DataIEEE Transactions on Signal Processing, 2015
- Weighted SPICE: A unifying approach for hyperparameter-free sparse estimationDigital Signal Processing, 2014
- Model-order selectionIEEE Signal Processing Magazine, 2004
- Joint space-time parameter estimation for wireless communication channelsIEEE Transactions on Signal Processing, 1998
- Implementation of the RELAX algorithmIEEE Transactions on Aerospace and Electronic Systems, 1998
- Efficient mixed-spectrum estimation with applications to target feature extractionIEEE Transactions on Signal Processing, 1996
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- ESPRIT-estimation of signal parameters via rotational invariance techniquesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Multiple emitter location and signal parameter estimationIEEE Transactions on Antennas and Propagation, 1986
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974