支持向量机方法用于民航安检炸药判别研究

Support vector machine applied to detection of explosives for aviation security examination

目前的民航安检X射线透视设备无法直接检出塑料炸药。国际上初步研究有效的γ射线共振技术可以透射瞬时测定行李中的物件的氮、氢、氧、碳含量。为与此技术配套,本工作应用对小样本集统计预报特别有效的支持向量机(support vectormachine,简称SVM)算法根据样品的氮、氢、氧、碳含量判别常见民用品和炸药,并用留一法比较SVM,Fisher法和人工神经网络算法的预报效果。结果表明SVM算法误报最少,且对所列炸药无一漏报。据此建立了炸药判别系统软件的原型,在实验室中模拟测试结果良好。

The currently used instruments for aviation security examination at airport are unable to detect explosives with great certainty. A newly invented nuclear technique, γ-ray resonance, can determine the element content of N, O, H and C in any point within hand luggage im-mediately.So it is necessary to build a software to make decision if it is explosive or not, based on the data obtained from 7-ray resonance. The SVM technique, a newly developed method of data mining, has been used to differentiate explosives and ordinary materials. It was found that the predictive ability of the SVM outperformed those of some traditional pattern recognition methods for the data set used here.