An efficient Newton-type method for the computation of ML estimators in a uniform linear array

@article{Selva2005AnEN,
  title={An efficient Newton-type method for the computation of ML estimators in a uniform linear array},
  author={Jesus Selva},
  journal={IEEE Transactions on Signal Processing},
  year={2005},
  volume={53},
  pages={2036-2045}
}
  • J. Selva
  • Published 2005
  • Computer Science, Mathematics
  • IEEE Transactions on Signal Processing
In the problem of estimating the angles of arrival to a uniform linear array, we present an efficient method to compute Maximum Likelihood (ML) estimations, based on the Modified Variable Projection (MVP) algorithm. In contrast to methods like Iterative Quadratical Maximum Likelihood (IQML) or the Iterative Method of Direction Estimation (IMODE), it is not based on a polynomial parameterization but on directly exploiting the Vandermonde structure through analytical tools like the Fast Fourier… Expand
Wideband DOA Estimation through Projection Matrix Interpolation
  • J. Selva
  • Computer Science, Mathematics
  • ArXiv
  • 2017
This paper presents a method to reduce the complexity of the deterministic maximum likelihood (DML) estimator in the wideband direction-of-arrival (WDOA) problem, which is based on interpolating theExpand
Efficient ML Direction of Arrival Estimation assuming Unknown Sensor Noise Powers
  • J. Selva
  • Mathematics, Computer Science
  • ArXiv
  • 2020
TLDR
The main contribution of this paper is the method's last step, in which a concentrated cost function is maximized in both the DOAs and noise powers in a few iterations through a Newton procedure. Expand
Improved Polynomial Rooting of Capon´s Algorithm to Estimate the Direction-of-Arrival in Smart Array Antenna
TLDR
It is shown that the root version of Capon method can provide more accurate angle estimation with less computational complexity than conventional Capon algorithm and also that the used modification plays a significant role in the performance's improvement ofCapon and its variant approaches. Expand
ML Estimation and Detection of Multiple Frequencies Through Periodogram Estimate Refinement
  • J. Selva
  • Mathematics, Computer Science
  • IEEE Signal Processing Letters
  • 2017
TLDR
The main advantage of the proposed method is its low complexity, given that its computational burden is just that of a few FFTs in typical scenarios. Expand
Efficient Wideband DOA Estimation Through Function Evaluation Techniques
  • J. Selva
  • Computer Science
  • IEEE Transactions on Signal Processing
  • 2018
TLDR
The method is a combination of the Chebyshev and barycentric interpolators, and makes use of the discrete cosine transform for reducing the complexity of the line searches in three wideband DOA estimators: incoherent multiple signal classification, test of orthogonality of projected subspaces, and deterministic maximum likelihood. Expand
Efficient Type 4 and 5 Nonuniform FFT Methods in the One-Dimensional Case
Abstract: The so-called non-uniform FFT (NFFT) is a family of algorithms for efficiently computing the Fourier transform of finitelength signals, whenever the time or frequency grid is nonuniformlyExpand
The Extended Invariance Principle for Signal Parameter Estimation in an Unknown Spatial Field
TLDR
It is shown how the extended invariance principle (EXIP) can be applied to obtain estimates with the quality of a spatially structured model, but with much lower complexity than directly utilizing a structured model and with greater robustness to errors in the model of the array response. Expand
Maximum Likelihood Parameter Estimation in a GNSS Receiver
The potential of the SAGE (Space Alternating Generalized Expectation Maximization) algorithm for navigation systems in order to distinguish the line-of-sight signal (LOSS) is to be considered. TheExpand
Efficient type-4 and type-5 non-uniform FFT methods in the one-dimensional case
  • J. Selva
  • Computer Science
  • IET Signal Process.
  • 2018
TLDR
The proposed methods roughly provide a factor-ten improvement on the FM and CG alternatives in computational burden and the Gaussian elimination, CG and FM methods are compared, both in terms of round-off error and computational burden. Expand
Rapid accurate frequency estimation of multiple resolved exponentials in noise
TLDR
This work proposes a fast yet accurate frequency estimator that combines an iterative frequency-domain interpolation step with a leakage subtraction scheme that is Fourier-based with no singular value decomposition or matrix inversion involved and the variance is extremely close to the CRLB. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 16 REFERENCES
Detection and estimation in sensor arrays using weighted subspace fitting
TLDR
A Gauss-Newton-type method is presented for solving the multidimensional WSF and maximum-likelihood optimization problems and a scheme for consistently estimating this is proposed based on an asymptotic analysis of the WSF cost function. Expand
The most efficient implementation of the IQML algorithm
  • Y. Hua
  • Mathematics, Computer Science
  • IEEE Trans. Signal Process.
  • 1994
TLDR
The present author gives a better way of implementation which requires computational flops of the order N and is also the most efficient in that no implementation can be made less than order N/sup 2/. Expand
Comparative study of IQML and MODE direction-of-arrival estimators
TLDR
It is shown that the amount of computations required by IQML is usually much larger than that required by MODE, especially for low signal-to-noise ratio (SNR) and a large number of snapshots. Expand
Newton-type methods in array processing
  • J. Selva
  • Mathematics, Computer Science
  • IEEE Signal Processing Letters
  • 2004
TLDR
This letter exploits compact expressions of the gradient, Hessian, and Hessian approximation of common maximum-likelihood (ML) cost functions, using a proper symbolic technique to derive conditional ML, row-correlated ML, and asymptotic ML cost functions. Expand
Maximum likelihood array processing for stochastic coherent sources
TLDR
The ML signal parameter estimator derived for the noncoherent case (or its large-sample realizations) asymptotically achieves the lowest possible estimation error variance (corresponding to the coherent Cramer-Rao bound). Expand
Exact and Large Sample ML Techniques for Parameter Estimation and Detection in Array Processing
TLDR
A vast number of algorithms has appeared in the literature for estimating unknown signal parameters from the measured output of a sensor array based on measurements of the array output. Expand
RELAX-based estimation of damped sinusoidal signal parameters
TLDR
Simulation results show that the performance of the extended RELAX algorithm can be better than that of the best available singular value decomposition based algorithm, especially when the noise is unknown and colored or when the number of data samples is large. Expand
Numerical methods for unconstrained optimization and nonlinear equations
TLDR
Newton's Method for Nonlinear Equations and Unconstrained Minimization and methods for solving nonlinear least-squares problems with Special Structure. Expand
Detection, Estimation, And Modulation Theory
Detection, estimation, and modulation theory , Detection, estimation, and modulation theory , مرکز فناوری اطلاعات و اطلاع رسانی کشاورزی
Numerical recipes in C
TLDR
The Diskette v 2.06, 3.5''[1.44M] for IBM PC, PS/2 and compatibles [DOS] Reference Record created on 2004-09-07, modified on 2016-08-08. Expand
...
1
2
...