A neural network-based smart antenna for multiple source tracking

Beamforming in 3G and 4G Mobile Communications: The Switched-Beam Approach

“…However, the drawback of these approaches is the need for intensive signal processing, like eigenvalue decomposition and signal autocorrelation matrix calculations. In order to avoid eigenvalue decomposition, NN-DoA finding procedures have been developed, which basically apply the mapping of the signal autocorrelation matrix with the signals' angles of arrival (AoA) (Christodoulou & Georgiopoulos, 2001;El Zooghby et al, 2000). A DoA estimation methodology has been firstly presented in (Gotsis et al, 2007), based on the mapping between the signals' AoA and the power measured at the input/output of the BFN.…”

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

“…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].…”

Neural Model for Far-Field 1D Localization of Mobile Stochastic EM Sources with Partially Correlated Radiation

“…The correlation matrix of signals received in Y 1 , Y 2 , ..., Y M sampling points can be obtained from the correlation matrix of antenna elements feed currents as (4) Because in our scenario the sources are moving in azimuth plane, it is assumed that j = 0 for any angular position of the source. In that case the angle position of s-th source in relation to m-th antenna array element is (5) while the distance of s-th source in relation to the m-th antenna array element is (6) Under angle position of s-th source in relation to antenna array θ S we mean its angle position in relation to the first element of the antenna array when θ S = θ S (1) . Using (3), (5) and (6) for given angle position of radiation source we may determine the mapping function M, and afterwards also the elements of the correlation matrix using (4).…”

“…These neural solutions may achieve same accuracy while gaining higher speeds in response. This is shown in [5][6][7][8][9][10][11], with a particular emphasis on neural models for 1D DoA estimation [6,7] and neural model for 2D DoA estimation of deterministic radiation sources [8].…”