A real multi-parent tri-hybrid evolutionary optimization methodwith applications in overlapping signal resolution

摘要

A real-coded multi-parent tri-hybrid evolutionary algorithm (EA)for problem optimization is presented. The hybrid EA algorithm combinesthe features of simplex, stochastic relaxation and multi-parent EAreproduction in a model that encourages competition among the bestindividual solutions front various operations. Its strength has beenevaluated using standard test functions and shown to do better thanother methods. The algorithm's ability to handle noise is evident whenapplied to experiments involving resolution of overlapping Wind Profilerdata Results obtained using ram data closely matched those obtained withdata preprocessed by a low pass FFT filter. Resolution of low-speed windand clutter signals in various degrees of overlap is made possible,thereby allowing the determination of wind velocity and variance to beexecuted with ease