2026-05-22T00:21:15.288Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:2:3279 2017-04-14T16:00:00Z 2

"Experimental Verification of an ANN Based Model for 2D DOA Estimation of Closely Spaced Coherent Sources" 2014 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/2/3279 http://onlinelibrary.wiley.com/doi/10.1002/mop.v56.11/issuetoc M. Stoilković Z. Stanković I. Milovanović N. Dončov Б. Миловановић T. Zwick This article presents development and validation of an artificial neural network (ANN)-based model for accurate two-dimensional direction of arrival estimation of two coherent sources. The ANN model is developed using simulated signals and its performance is evaluated by measurements inside an anechoic chamber. Simulations and experiments show good agreement in estimating both azimuth and elevation angles of coherent sources. The proposed model demonstrates ability to separate two closely spaced sources and outperforms MUSIC with spatial smoothing preprocessing in the case of small number of signal snapshots. © 2014 Wiley Periodicals, Inc. Microwave Opt Technol Lett 56:2558–2562, 2014 article 10.1002 56 11 2558 2562 0895-2477 MICROWAVE AND OPTICAL TECHNOLOGY LETTERS