EFFICIENT NEURAL NETWORK APPROACH FOR 2D DOA ESTIMATION BASED ON ANTENNA ARRAY MEASUREMENTS

被引：39

作者：

Agatonovic, Marija ^{[1
]}

Stankovic, Zoran ^{[1
]}

Milovanovic, Ivan ^{[2
]}

Doncov, Nebojsa ^{[1
]}

Sit, Leen ^{[3
]}

Zwick, Thomas ^{[3
]}

Milovanovic, Bratislav ^{[1
]}

机构：

[1] Univ Nis, Fac Elect Engn, Nish 18000, Serbia

[2] Singidunum Univ, Belgrade 11000, Serbia

[3] Karlsruhe Inst Technol, Inst Hochfrequenztech & Elekt, D-76131 Karlsruhe, Germany

来源：

PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER | 2013年 / 137卷

关键词：

OF-ARRIVAL ESTIMATION; 2-D DOA; ALGORITHM; ESPRIT; MUSIC; FIELD;

D O I：

10.2528/PIER13012114

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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 super-resolution 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.

引用

页码：741 / 758

页数：18

共 41 条

[21] PREDICTION OF THE ELECTROMAGNETIC FIELD IN METALLIC ENCLOSURES USING ARTIFICIAL NEURAL NETWORKS [J].

Luo, M. ;

Huang, K. .

PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER, 2011, 116 :171-184

[22]

MARIN Alejandro., 2012, Portafolio de experiencia profesional, P1

[23] 2D DOA estimation using beam steering antenna by the switched parasitic elements and RBF neural network [J].

Matsumoto, T ;

Kuwahara, Y .

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART I-COMMUNICATIONS, 2006, 89 (09) :22-31

[24] SPIKING NEURAL NETWORKS FOR BREAST CANCER CLASSIFICATION IN A DIELECTRICALLY HETEROGENEOUS BREAST [J].

O'Halloran, M. ;

McGinley, B. ;

Conceicao, R. C. ;

Morgan, F. ;

Jones, E. ;

Glavin, M. .

PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER, 2011, 113 :413-428

[25]

Pister K. S. J., 2011, PROGR ELECTROMAGNETI, V116, P243

[26]

Pourahmadi M., 2012, Progress In Electromagnetics Research B, V40, P261

[27] Direction of arrival estimation based on support vector regression: Experimental validation and comparison with MUSIC [J].

Randazzo, A. ;

Abou-Khousa, M. A. ;

Pastorino, M. ;

Zoughi, R. .

IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS, 2007, 6 :379-382

[28] ESPRIT - ESTIMATION OF SIGNAL PARAMETERS VIA ROTATIONAL INVARIANCE TECHNIQUES [J].

ROY, R ;

KAILATH, T .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (07) :984-995

[29]

Sarevska M, 2004, NEUREL 2004: SEVENTH SEMINAR ON NEURAL NETWORK APPLICATIONS IN ELECTRICAL ENGINEERING, PROCEEDINGS, P85

[30]

Sarevska M., 2005, WSEAS Transactions on Communications, V4, P556

← 1 2 3 4 5 →