Title :
Applying genetic algorithm to modeling nonlinear transfer functions
Author :
Loyka, Sergey L.
Author_Institution :
Swiss Fed. Inst. of Technol., Lausanne, Switzerland
Abstract :
A genetic algorithm (GA) technique for the approximation of nonlinear transfer functions is proposed in this paper. It is shown that the GA approximation method gives better accuracy than the classical Chebyshev approximation, which is sometimes considered to be the best one on the minimax criterion. Application of this technique to behavioral-level simulation is also discussed
Keywords :
Chebyshev approximation; function approximation; genetic algorithms; minimax techniques; nonlinear functions; polynomial approximation; transfer functions; Chebyshev approximation; approximation method; behavioral-level simulation; genetic algorithm technique; minimax criterion; modeling; nonlinear transfer functions; Approximation methods; Chebyshev approximation; Computational modeling; Function approximation; Genetic algorithms; Genetic mutations; Minimax techniques; Polynomials; System performance; Transfer functions;
Conference_Titel :
Telecommunications in Modern Satellite, Cable and Broadcasting Services, 1999. 4th International Conference on
Conference_Location :
Nis
Print_ISBN :
0-7803-5768-X
DOI :
10.1109/TELSKS.1999.804737