Title :
The combination of neural networks and genetic algorithm for fast and flexible wide ing in digital beamforming
Author :
Wang, Yun ; Lu, Yilong
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
Abstract :
The paper presents an approach of using neural networks to apply slow genetic algorithm solutions for real time applications. Genetic algorithms (GAs) are powerful optimization tools which have been applied to solve many complicated problems in a very wide range of areas. However, GA slowness prevent it from being used in real-time systems. A radial basis function neural network (RBFNN) is exploited to approximate the genetic algorithm´s function. This GA-RBFNN approach makes powerful yet slow genetic algorithm solutions possible for real-time problems. As an example, we have successfully applied the proposed approach for fast solution of the GA based wide ing problem in adaptive digital beamforming.
Keywords :
adaptive systems; antenna arrays; genetic algorithms; radial basis function networks; real-time systems; signal processing; GA based wide ing problem; GA-RBFNN; adaptive digital beamforming; flexible wide ing; neural networks; optimization tools; radial basis function neural network; real time applications; slow genetic algorithm solutions; Adaptive arrays; Adaptive systems; Array signal processing; Broadband antennas; Genetic algorithms; Intelligent networks; Jamming; Neural networks; Radar antennas; Real time systems;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1198165