Target Recognition Study based on the Dynamic Support Vector Machine
The dynamic support vector machine is put forward by integrating the target feature with the support vector machine (SVM) in the paper, whose primary role is recognition of the target feature. The dynamic SVM does not search the optimal separating hyperplane of the whole space, but searches the optimal separating hyperplane of the local space taking the target feature as center. To show better importance of each sample to the target feature, a method is put forward that the penalty function Ci is measured by using the distance between the target feature and each training sample. The dynamic SVM is trained after the dynamic training set is reconstructed according to the penalty function Ci. At last, the dynamic SVM is applied to the underwater target recognition that is utmost important to submarine war. Experiment results show that the dynamic SVM is more robust in the underwater target recognition.
support vector machine dynamic support vector machine penalty function Ci, underwater target recognition.
SHI Guangzhi HU Junchuan XUE Changyou SONG Rugang
Department of Navigation and Communication Navy Submarine Academy Qingdao, Shandong Province 266071, China
国际会议
武汉
英文
656-659
2007-07-25（万方平台首次上网日期，不代表论文的发表时间）