Abstract :
In this paper, the algorithm combined the construction methods of immune strategies and immune operator, better solved the degradation phenomenon appeared in the algorithm, and the convergence speed has been improved significantly. Comparing with the differential evolution algorithm, adding differential evolution operator in the immune algorithm can increase antigen recognition, memory function and regulatory function. This algorithm not only failed to reduce the differential evolution algorithm robustness, but also took into account the global and local search capabilities; at the same time, the selection strategy based on antibody concentration made up the shortcomings of the algorithm to be easy fall into local excellent when the group diversity is bad, which improved the algorithm group diversity.
Keywords :
artificial immune systems; evolutionary computation; neural nets; pattern recognition; algorithm group diversity; antigen recognition; differential evolution algorithm; differential evolution operator; evolution immune algorithm; immune operator; memory function; neural network; regulatory function; search capabilities; Approximation algorithms; Convergence; Diversity reception; Evolutionary computation; Genetic algorithms; Immune system; Neural networks; Radial basis function networks; Robustness; Simulated annealing; differential; diversity; evolution immunity; neural network;
