Research on Support Vector Machine Parameters Optimization in High Range Resolution Radar Target Classification

摘要：

Parameters have a great impact on performance of Support Vector Machine (SVM) classifier. Parameters optimization is the bottleneck of restricting SVM application. Aiming at radar target classification, one parameters optimization algorithm based on improved Genetic Algorithm (GA) is proposed. The fitness function selection of GA in high range resolution radar target classification is studied firstly. By comparing estimation precision, computing time cost and robustness, the fitness function fit for high range resolution radar target classification is acquired. Then the relationship between parameters and SVM generalization ability is studied and searching scopes of different parameters are determined. Finally, one parameter optimization algorithm based on improved GA is given which can perform feature extraction and adjust the crossover ratio and mutation ratio automatically. By classifying radar range profiles of three targets, the effectiveness of the algorithm is testified.

关键词： Support Vector Machine Parameters optimization Generalization error estimation HRRP Genetic algorithm

作者: Minghua Shen Huaitie Xiao Qiang Fu

作者单位: School of Electronic Science and Engineering, National University of Defense and Technology, Changsh ATR Key Lab of the National University of Defense and Technology, Changsha, Hunan, 410073, P.R.China

会议类型: 国际会议

会议名称: The Second International Symposium on Intelligence Computation and Applications(ISICA 2007)(第二届智能计算及其应用国际会议)

会议地点: 武汉

会议语种:英文

在线出版日期: 2007-09-21（万方平台首次上网日期，不代表论文的发表时间）