Battlefield Target Identification Based on Improved Grid-Search SVM Classifier

Choosing the kernel and error penalty parameters for support vector machine (SVM) is very important for the performance of classifiers. An improved grid-search algorithm is proposed to choose the optimal parameters of SVM. The battlefield multi-target SVM classifier is designed using this algorithm. Also three classifiers including k-nearest neighborhood classifier, improved BP neural network classifier and SVM classifier are used to do the comparison experiments of targets classification. Result shows that the improved grid-search algorithm can reduce the SVM classifier's computational complexity effectively and improve its performance and classification accuracy.