Multi kernel SVM evaluation of UAV air ground combat effectiveness based on AFSA

In order to improve the attack effect of UAV on ground targets and the ability to complete the scheduled combat tasks, an air ground combat effectiveness evaluation method based on artificial fish swarm algorithm (AFSA) and support vector machine (SVM) is proposed.In this method, firstly, according to the local optimization characteristics of radial basis function and global optimization characteristics of polynomial kernel function,In this paper, a hybrid kernel function is constructed for SVM in linear weighted form. Then, the parameters of multi-core SVM are optimized by AFSA, and the air ground combat effectiveness evaluation model of UAV is constructed.The simulation results show that the method has a high evaluation accuracy for UAV air to ground combat effectiveness, and it is better than SVM method with single radial basis function kernel or polynomial kernel,So as to confirm its effectiveness and feasibility.