Performance of radial-basis function networks for direction of arrival estimation with antenna arrays

Zooghby, A.H. El; Christodoulou, C.G.; Georgiopoulos, Michael

doi:10.1109/8.650072

Cited by 188 publications

(108 citation statements)

References 10 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Parameter vector always lies in the subspace spanned by the training data and, according to the representer theorem [37], it can be constructed as a linear combination of the given data (8) where are the training data pairs. Then, estimator (7) can be rewritten as (9) In this context, 's are called primal parameters, and 's are the dual ones. The problem of optimizing the estimator expressed as in (9) is called a dual problem, and it is useful for those cases where the primal problem is unsolvable in a direct way.…”

Section: Estimators In Reproducing Kernel Hilbert Subspacesmentioning

confidence: 99%

See 1 more Smart Citation

Approximate Kernel Orthogonalization for Antenna Array Processing

Navia-Vázquez

Martínez‐Ramón

García-Muñoz

et al. 2010

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

Abstract-We present a method for kernel antenna array processing using Gaussian kernels as basis functions. The method firs identifie the data clusters by using a modifie sparse greedy matrix approximation. Then, the algorithm performs model reduction in order to try to reduce the fina size of the beamformer. The method is tested with simulations that include two arrays made of two and seven printed half wavelength thick dipoles, in scenarios with 4 and 5 users coming from different angles of arrival. The antenna parameters are simulated for all DOAs, and include the dipole radiation pattern and the mutual coupling effects of the array. The method is compared with other state-of-the-art nonlinear processing methods, to show that the presented algorithm has near optimal capabilities together with a low computational burden.

show abstract

Section: Estimators In Reproducing Kernel Hilbert Subspacesmentioning

confidence: 99%

“…This feature decreases estimation errors or bit error rates. Neural networks [4] have been proposed for beamforming (e.g., [5]- [7]) and direction of arrival estimation (e.g., [8], [9]) among other array processing tasks. A com-A.…”

mentioning

confidence: 99%

Approximate Kernel Orthogonalization for Antenna Array Processing

Navia-Vázquez

Martínez‐Ramón

García-Muñoz

et al. 2010

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

show abstract

“…Compared to conventional signal processing algorithms that are mainly based on linear models, neural networks consider DOA estimation as approximation of highly nonlinear multidimensional function, or in other words, as a mapping between spatial covariance matrix of received signals from antenna elements and DOAs. There are many publications on ANNs in DOA estimation of both narrowband and wideband signals [22][23][24][25][26][27][28][29][30][31]. Most of them report results on Radial Basis Function Neural Network (RBF-NN) modeling to estimate DOAs in azimuth plane only, but there are also papers addressing two-dimensional DOA estimation [32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

Efficient Neural Network Approach for 2d Doa Estimation Based on Antenna Array Measurements

Agatonovic¹,

Stankovic²,

Milovanović³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-In this paper, we present an efficient Artificial Neural Network (ANN)-based model to estimate both azimuth and elevation arrival angles of a signal source. To achieve this goal, the ANN model is constructed using measurement data obtained by a rectangular antenna array in the space-frequency domain. Unlike classical superresolution algorithms such as 2D MUSIC, the proposed model is capable to account for imperfections of measurement equipment as well as mutual couplings between array elements. The neural model has been verified for several angular positions and frequencies. It is shown that the use of ANN model to estimate angular positions of a signal source yields more accurate results when compared to 2D MUSIC. Moreover, the neural model significantly outperforms 2D MUSIC in terms of speed of computation.

show abstract

“…Ability and adaptability to learn, generalisability, fast real-time operation, and ease of implementation have made NNs popular for a number of microwave design problems in recent years [2]. Citing just a number of examples: NNs have been used in the design of passive microwave circuits [3], analysis and synthesis of microstrip lines [4], calculation of the characteristic impedance of air-suspended trapezoidal and rectangular-shaped microshield lines [5], design of nonlinear microwave circuits based on active devices [6], design of microstrip patch antennas [7,8], direction of arrival estimation with antenna arrays [9,10], radar target recognition [11], aperture antenna shape prediction [12], inverse scattering of dielectric cylinders [13], near field to far filed transformation [14], and synthesis of antenna array [15,16]. In addition to modeling the response, NNs can also be employed within the core of the full-wave solvers based on the method of moments [17,18].…”

Section: Introductionmentioning

confidence: 99%

Neural Frequency Sweeper for Accelerating S-Parameters Calculation of Planar Microwave Structures

Soliman¹,

Ibrahim²

2008

PIER M

View full text Add to dashboard Cite

Abstract-This paper presents a new frequency-sweep approach for the efficient calculation of S-parameters of planar microwave structures. The approach is based on approximating the frequency dependence of the real and imaginary parts of the S-parameters using neural networks. Due to its superior performance, radial basis functions neural network (RBF-NN) is adopted. A limited number of frequency samples are used to train the RBF-NN. Then, the trained RBF-NN is capable of providing a smooth frequency response with very high accuracy in a fraction of a second. The proposed method is applied to a number of planar microwave structures such as: Patch antenna with an inset feed, band-rejection filter, and branch-line coupler. According to the presented results, a speed factor of at least 10 is measured, and a maximum percentage error of 3.29% is recorded.

show abstract

Performance of radial-basis function networks for direction of arrival estimation with antenna arrays

Cited by 188 publications

References 10 publications

Approximate Kernel Orthogonalization for Antenna Array Processing

Approximate Kernel Orthogonalization for Antenna Array Processing

Efficient Neural Network Approach for 2d Doa Estimation Based on Antenna Array Measurements

Neural Frequency Sweeper for Accelerating S-Parameters Calculation of Planar Microwave Structures

Contact Info

Product

Resources

About