A Novel Radar Target Recognition Algorithm Based on SVM

To solve the problems and defections of existing methods of support vector machine (SVM) classification, an improved Gaussian kernel based on SVM is proposed and a improved SVM model selection scheme combining leave-one-Out method with one-validation method is presented in this paper, Based on the high resolution range profile (HRRP) of three types of target, a preprocessing method is introduced, the novel classification algorithm for HRRP based on the improved SVM is applied. Finally, experimental results prove that the improved SVM classifier has better performance on target-aspect stability, training set-size stability and anti-noise ability than traditional SVM.