Intelligent beamforming by using a complex-valued neural network

Issue title: Engineering applications of Computational Intelligence

Article type: Research Article

Authors: Suksmono, Andriyan Bayu | Hirose, Akira

Affiliations: Department of Electrical Engineering, Institut Teknologi Bandung, Jl. Ganesha No. 10, Bandung 40132, Indonesia | Department of Electrical and Electronic Engineering, University of Tokyo 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

Note: [] Corresponding author. E-mail: suksmono@yahoo.com; suksmono@ltrgm.ee.itb.ac.id

Abstract: This paper describes an intelligent beamforming (IBF) system based on complex-valued neural network (CVNN). A multilayer network structure with complex-valued neurons has been used. The system employs the complex-valued backpropagation algorithm (CVBPA) to intelligently adapt incoming signals impinging to sensors array. Performance of the CVNN-IBF system is compared with that of the conventional single-layer adaptive system using complex-valued least mean square (CLMS) algorithm. Experiments for multiple beam-pointing and multiple null-steering demonstrate that the CVNN-IBF outperforms the CLMS one in terms of convergence speed and interferences suppression levels.

Journal: Journal of Intelligent & Fuzzy Systems, vol. 15, no. 3-4, pp. 139-147, 2004