Two-dimensional DOA estimation based on a single Uniform linear array

Conventional DOA estimation techniques use planar arrays to determine both azimuth and elevation angles due to angle ambiguity resulting in ULA radiation pattern symmetry. This paper demonstrates the ability of a single Uniform Linear Array (ULA) of isotropic elements along with an Artificial Neural Networks (ANN) approach to achieve two-dimensional direction of arrival (2D-DOA) estimation. A single linear array combined with appropriately trained Linear Vector Quantization (LVQ) Artificial Neural Networks is used to achieve two-dimensional direction of arrival (2D-DOA) estimation with elevation and azimuth angles estimations. Linear Vector Quantization (LVQ) neural networks are sequentially trained on elevation and azimuth dependent datasets build from received signal in predefined spatial sectors chosen in accordance with pattern symmetry and radiation intensity. A multilevel process is applied to further reduce the training sets sizes and computation time. System performances are in good agreement with subspace based techniques.