Performance evaluation of an artificial neural network-based adaptive antenna array system

  • Authors:

  • Muamar Al-Bajari;Jamal M. Ahmed;Mustafa B. Ayoob

  • Affiliations:

  • Electrical Engineering and Computer Science Dept., TU, Berlin, Germany;Department. of Communication, University of Mosul-Iraq;Department. of Communication, University of Mosul-Iraq

  • Venue:
  • EvoCOMNET'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Efficient tracking systemsare needed to constantly track multiple desired signals simultaneously in different modern wireless applications such as mobile communication, radar, and localization. The adaptive antenna tracking system presented in this paper mainly consists of three units: data processing, Artificial Neural Network Processor (ANNP) and the optimum weights processing. The data processing unit is used to calculate the correlation matrix of the received signals, which is eventually handled by the ANNP unit. The ANNP unit is based on the architecture of a family of Radial Basis Function Neural Network (RBFNN) to perform both detection and Direction of Arrival (DOA) estimation. The optimum weights processing unit utilizes the Linear Constraint Minimum Variance (LCMV) approach, using the estimated angles of the desired signals generated by the ANNP unit, to calculate the steering matrix of the AAA system. The performance evaluation of the system is conducted experimentally using simulation techniques in a variety of angular separations, number of sources and various Signal to Noise Ratios (SNRs).