A Neural-Network-Based Beamformer for Phased Array Weather Radar

Sallam, Tarek; Abdel‐Rahman, Adel B.; Alghoniemy, Masoud; Kawasaki, Zen; Ushio, Tomoo

doi:10.1109/tgrs.2016.2554116

Cited by 39 publications

(30 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to [23,24] for training the CNN, the pre-processed form of the received signal autocorrelation matrix is required. All elements of the received signal autocorrelation matrix are not needed for training.…”

Section: Trainingmentioning

confidence: 99%

“…The input of the DNN is the pre-processed autocorrelation matrix of the received signal and the output is the DOA of the desired signals. In [22][23][24] a radial-basis-function NN with the same input is used to estimate either the DOA of the desired signals or the proper weight vectors of the antenna arrays. In [25], a feedforward NN uses the prior knowledge about DOA of the desired signal and interferences to achieve high SINR and low sidelobe levels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep‐learning‐based beamforming for rejecting interferences

Ramezanpour

Rezaei

Mosavi

2020

IET signal process.

View full text Add to dashboard Cite

Antenna arrays have been widely used for space and space-time processing to estimate the desired signals in the presence of narrowband and wideband interferences. Estimating the optimal weight vector is a challenging problem in space and space-time processing due to its high computational complexity. The problem escalates when the number of antennas and taps of filters for time-domain processing increases. In this study, a convolutional neural network is employed to estimate nearlyoptimal weight vectors even when the number of available snapshots of the received signal is as low as 400 and a signal-tonoise ratio as low as −5 dB. Unlike the conventional processors, the authors proposed method requires no prior knowledge about the direction of arrival of the desired signal. In addition, due to its parallel architecture, the computational complexity of the neural processors is reasonable using a single graphical processing unit on a PC to run the algorithms. Through simulations of the uniform linear array in the presence of narrowband and wideband interferences, they demonstrate that the output signal-tointerference plus noise ratio (SINR) is very close (by <0.5 dB) to the max SINR obtained by the optimal weight vector of antenna arrays.

show abstract

Section: Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep‐learning‐based beamforming for rejecting interferences

Ramezanpour

Rezaei

Mosavi

2020

IET signal process.

View full text Add to dashboard Cite

show abstract

“…Beamforming. The cross-polarization pattern could be suppressed by using the beamforming algorithm [28]. A spacetime-polarization filter structure is proposed for the pattern synthesis of the conformal phased array, and the alternating projection method is used to depress the cross-polar level in [29].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Direction-Dependent Polarization State Configuration Method for High Isolation in Polarimetric Phased Array Radar

Wang¹,

Yin²,

Pang³

et al. 2020

Preprint

View full text Add to dashboard Cite

<div>High cross-polarization isolation (CPI) is crucial to the accurate polarization measurement using polarimetric phased array radar (PPAR). In this paper, we propose an adaptive direction-dependent polarization state configuration (AD2PSC) method to improve the polarization isolation. Compared with conventional fixed polarization state of radiated wave whether it is linear, circular or elliptical polarization state, our AD2PSC approach configures the polarization state on basis of beam steering. To achieve the adaptive configuration of magnitude and phase of the dual-polarization antenna, an improved steepest descent algorithm is put forward. To facilitate the uniform representation for the polarization measurement application of PPAR, the universal expressions of intrinsic and measured backscatter matrices are derived for arbitrary polarization state. The dualpolarization dipole array is used to assess the priority of our proposed method. Compared with the conventional approaches,</div><div>our approach could obtain higher CPI while being available for a larger scanning range. The configured CPI meets the specific polarization requirement for PPAR.</div>

show abstract

“…How to improve the performance of direction of arrival (DOA) estimation, many experts and scholars have made a great deal of research. In general, there are three categories of array signal processing approaches to solving the problem, high‐resolution techniques [5–9], maximum‐likelihood (ML) techniques [10–13] and neural network techniques [14–21].…”

Section: Introductionmentioning

confidence: 99%