Konstantinos A. Gotsis

TL;DR: A generic direction of arrival (DoA) estimation methodology is presented that is based on neural networks and designed for a switched-beam system (SBS), and can be applied to current cellular communications base stations, promoting the wider use of smart antenna beamforming.

TL;DR: A new memetic multi-objective evolutionary algorithm namely the memetic generalized differential evolution (MGDE3) is introduced, a memetic extension of the popular GDE3 algorithm, providing an extensive set of solutions for each design case.

TL;DR: An alternative procedure for the prediction of propagation path loss in urban environments, which is based on artificial neural networks (ANNs), and applies a recently proposed Differential Evolution (DE) algorithm in order to design an optimal ANN for path-loss propagation prediction.

TL;DR: A new adaptive beamforming technique based on neural networks (NNs) is proposed and the extracted radiation patterns are compared to respective patterns extracted by the MBPSO and a well-known robust adaptive beamforms technique called Minimum Variance Distortionless Response (MVDR).

TL;DR: A comparative study of neural network (NN) training exhibits the superiority of the NN trained by the MBPSO over well known beamforming method called Minimum Variance Distortionless Response.