A cascade-connected neural model for improved 2D DOA estimation of an EM signal
Corresponding Author
Marija Stoilkovic
Innovation Centre of Advanced Technologies, Bvd. Nikole Tesle 61/5, 18000 Nis, Serbia
Correspondence to: Marija Stoilkovic, Innovation Centre of Advanced Technologies, Bvd. Nikole Tesle 61/ 5, 18000 Nis, Serbia.
E-mail: [email protected]
Search for more papers by this authorZoran Stankovic
Faculty of Electronic Engineering, University of Nis, Aleksandra Medvedeva 14, 18000 Nis, Serbia
Search for more papers by this authorBratislav Milovanovic
Faculty of Electronic Engineering, University of Nis, Aleksandra Medvedeva 14, 18000 Nis, Serbia
Search for more papers by this authorCorresponding Author
Marija Stoilkovic
Innovation Centre of Advanced Technologies, Bvd. Nikole Tesle 61/5, 18000 Nis, Serbia
Correspondence to: Marija Stoilkovic, Innovation Centre of Advanced Technologies, Bvd. Nikole Tesle 61/ 5, 18000 Nis, Serbia.
E-mail: [email protected]
Search for more papers by this authorZoran Stankovic
Faculty of Electronic Engineering, University of Nis, Aleksandra Medvedeva 14, 18000 Nis, Serbia
Search for more papers by this authorBratislav Milovanovic
Faculty of Electronic Engineering, University of Nis, Aleksandra Medvedeva 14, 18000 Nis, Serbia
Search for more papers by this authorSummary
This article proposes a neural network-based approach to increase accuracy of two-dimensional direction of arrival (DOA) estimation of an electromagnetic signal. The proposed method combines two neural networks developed using simulated and small amount of empirical data, respectively. The output of the simulation-based neural network represents approximate information on DOAs. It is then considered as a priori knowledge for the small empirical network that is crucial for obtaining more accurate DOA estimates. The developed cascade-connected model is validated using real data from a rectangular antenna array. Improvements in terms of accuracy and reliability are obtained and compared with the MUSIC algorithm. Copyright © 2015 John Wiley & Sons, Ltd.
References
- 1Molisch AF. Wireless Communications. Wiley-IEEE Press: UK, 2010.
- 2Pillai SU. Array Signal Processing. Springer-Verlag: New York, 1989.
10.1007/978-1-4612-3632-0 Google Scholar
- 3Schmidt R. Multiple emitter location and signal parameter estimation. IEEE Trans Antenn Propag 1986; 34: 276–280.
- 4Roy R, Kailath T. ESPRIT—estimation of signal parameters via rotational invariance techniques. IEEE Trans Acoust Speech Signal Process 1989; 37: 984–995.
- 5Rao BD, Hari KVS. Performance analysis of root-MUSIC. IEEE Trans Acoust Speech Signal Process 1989; 37: 1939–1949.
- 6Pillai SU, Kwon BH. Forward/backward spatial smoothing techniques for coherent signal identification. IEEE Trans Acoust Speech Signal Process 1989; 37: 8–15.
- 7Ottersten B, Viberg M, Kailath T. Performance analysis of the total least squares ESPRIT algorithm. IEEE Trans Signal Process 1991; 39: 1122–1134.
- 8Mathews CP, Zoltowski MD. Eigenstructure techniques for 2-D angle estimation with uniform circular arrays. IEEE Trans Signal Process 1994; 42: 2395–2407.
- 9Ferreol A, Boyer E, Larzabal P. Low cost algorithm for some bearing estimation methods in presence of separable nuisance parameters. Electron Lett 2004; 40: 966–967.
- 10Hou YS, Yong J, Zhang LJ. Low cost algorithm for azimuth-elevation joint estimation. 9th International Conference on Signal Processing ICSP 2008; pp. 92–95. DOI: 10.1109/ICOSP.2008.4697076
- 11Tayem N, Kwon HM. L-shaped 2-dimensional arrival angle estimation with propagator method. IEEE Trans Antenn Propag 2005; 53: 1622–1630.
- 12Gan L, Gu JF, Wei P. Estimation of 2-D DOA for noncircular sources using simultaneous SVD technique. IEEE Antenn Wireless Propag Lett 2008; 7: 385–388.
- 13Lin M, Cao LL, Ouyang J, Shi W, An K. DOA estimation using virtual array technique for noncircular signals. 2012 International Conference on Wireless Communications & Signal Processing (WCSP) 2012; pp. 1–5. DOI: 10.1109/WCSP.2012.6542875
- 14Donelli M, Viani F, Rocca P, Massa A. An innovative multiresolution approach for DOA estimation based on a support vector classification. IEEE Trans Antenn Propag 2009; 57: 2279–2292.
- 15Xu X, Ye Z. Two-dimensional direction of arrival estimation by exploiting the symmetric configuration of uniform rectangular array. IET Radar Sonar Nav 2012; 6: 307–313.
- 16Chen J, Shuxun W, Lin L. Two-dimensional DOA estimation of coherent signals based on 2D unitary ESPRIT method. 8th Int Conf Signal Process 2006; 1: 16–20.
- 17Randazzo A, Abou-Khousa MA, Pastorino M, Zoughi R. Direction of arrival estimation based on support vector regression: experimental validation and comparison with MUSIC. IEEE Antenn Wireless Propag Lett 2007; 6: 379–382.
- 18Swindlehurst A, Kailath T. A performance analysis of subspace-based methods in the presence of model errors: part 1—the MUSIC algorithm. IEEE Trans Signal Process 1992; 40(7): 1758–1774.
- 19Swindlehurst A, Kailath T. A performance analysis of subspace-based methods in the presence of model errors: part & multidimensional algorithms. IEEE Trans Signal Process 1993; 41(9): 2882–2890.
- 20Zhang QJ, Gupta KC. Neural Networks for RF and Microwave Design. Artech House: Boston, MA, 2000.
- 21El Zooghby AH, Christodoulou CG, Georgiopoulos M. A neural network-based smart antenna for multiple source tracking. IEEE Trans Antenn Propag 2000; 48: 768–776.
- 22Wang M, Yang S, Wu S, Luo F. A RBFNN approach for DOA estimation of ultra wideband antenna array. Neurocomputing-Elsevier 2008; 71: 631–640.
- 23Matsumoto T, Kuwahara Y. 2D DOA estimation using beam steering antenna by the switched parasitic elements and RBF neural network. Electron Commun Jpn (Part 1: Commun) 2006; 89: 22–31.
- 24Parhizgar N, Alighanbari A, Masnadi-Shirazi MA, Sheikhi A. A modified decoupling scheme for receiving antenna arrays with application to DOA estimation. Int J RF Microwave Comput—Aided Eng 2013; 23: 246–259.
- 25Yu Y, Lui HS, Niow CH, Hui HT. Improved DOA estimations using the receiving mutual impedances for mutual coupling compensation: an experimental study. IEEE Trans Wireless Commun 2011; 10: 2228–2233.
- 26Kuwahara Y, Matsumoto T. Experiments on direction finder using RBF neural network with post-processing. Electron Lett 2005; 41: 602–603.
- 27Matsumoto T, Kuwahara Y. 2D DOA estimation using beam steering antenna by the switched parasitic elements and RBF neural network. Electron Commun Jpn Part 1 2006; 89: 1500–1508.
- 28Fonseca NJG, Coudyser M, Laurin JJ, Brault JJ. On the design of a compact neural network-based DOA estimation system. IEEE Trans Antenn Propag 2010; 58: 357–366.
- 29Agatonovic M, Stankovic Z, Doncov N, Sit L, Milovanovic B, Zwick T. Application of artificial neural networks for efficient 2D DOA estimation. Radioengineering 2012; 21: 1178–1186.
- 30Agatonovic M, Stankovic Z, Milovanovic I, Doncov N, Sit L, Zwick T, Milovanovic B. Efficient neural network approach for 2D DOA estimation based on antenna array measurements. Prog Electromagn Res—PIER 2013; 137: 741–758.
- 31Agatonovic M, Stankovic Z. Hybrid ANN model for accurate 2D DOA estimation of a radiating source. TELSIKS 2013; 2: 370–373. doi:10.1109/TELSKS.2013.6704401.
10.1109/TELSKS.2013.6704401 Google Scholar
