Dynamic Target Recognition Study Using the Support Vector Machine And Expert Knowledge

摘要：

A dynamic recognition method is researched,which is made up of the SVM based on target feature and expert system. The dynamic recognition method makes full use of the advantage of SVM and expert system, whose role is recognition of the target feature.To show better importance of each sample to the target feature, a metrical method of the sample penalty term is put forward. The penalty term of each sample is made up of the distance penalty term and prior penalty term.Moreover, the expert knowledge of demodulation line spectrum feature extracted from ship radiated-noise is obtained by the sample analysis. At last, the dynamic target recognition method using SVM and expert knowledge is applied to the underwater acoustic target recognition. Experiment results show the method using SVM and expert knowledge enhances recognition rate and recognition efficiency.

关键词： support vector machine (SVM) SVM based on target feature underwater acoustic target recognition penalty function expert knowledge

作者: Guangzhi Shi Junchuan Hu Yuyang Li Mei Han

作者单位: Department of Navigation and Communication Navy Submarine Academy 266071, Qingdao, China

会议类型: 国际会议

会议名称: The International Colloquium on Onformation Fusion 2007(2007年国际信息融合研讨会)

会议地点: 西安

会议语种:英文

页码: 290-295

在线出版日期: 2007-08-22（万方平台首次上网日期，不代表论文的发表时间）