摘要
针对已有空袭目标识别方法存在的不足,依据空袭目标的分类原则,提出了基于多类分类支持向量机的空袭目标识别方法。该方法采用支持向量机的多类分类技术,降低了经验风险,有效地提高了识别率。最后给出了一个算例,结果和专家给出的建议一致,表明支持向量机方法比较精确和简单。
New recognition method of air-attack targets based on multi-class classification Support Vector Machine (SVM) which overcomes defects of existing air-attack targets identification measures effectively is put forward. The method adopts technique of multi-class classification support vector machine, reduces the experience risk, and improves the rate of identification. At last an example is given, and the computed results are accordant with the experts’advice, show that the support vector machine is more accur...
出处
《微计算机信息》
北大核心
2008年第10期258-260,共3页
Control & Automation
基金
论文受陕西省自然科学基金项目(2006F18)
关键词
支持向量机
目标识别
多类分类
support vector machine
targets recognition
multi- class classification