基于主成分分析和Mahalanobis距离的异常γ能谱识别  

Anomaly gamma spectra detection based on principal component analysis and the Mahalanobis distance

作　　者：赵日[1,2] 刘立业[2] 李君利[1] 

机构地区：[1]清华大学工程物理系,北京100084 [2]中国辐射防护研究院,太原030006

出　　处：《清华大学学报（自然科学版）》2017年第8期826-831,共6页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金项目(11605162)

摘　　要：为了提高货物或人体放射性筛查的可靠性,提出了一种基于主成分分析和Mahalanobis距离的异常γ能谱识别方法。该方法首先对大量不含异常放射性的测量对象产生的正常γ能谱进行主成分分析,提取出其所有主成分,并按从大到小的顺序,选取前若干主成分构成子空间;将正常及待识别γ能谱在此子空间上投影,得到它们的Mahalanobis距离,通过比较这些距离的相对大小实现对异常γ能谱的识别。Monte Carlo模拟实验和实际测试实验表明,在子空间信息量占原始信息比例大于99%时该方法可靠有效。A principai component analysis （PCA） and Mahalanobis distance （MD） based anomaly gamma spectra detection method is developed to improve the reliability of radiation scanning of goods and human bodies. This method first extracts all the principal components （PCs） of large numbers of benign gamma spectra by PCA and selects several largest PCs to form a subspace. The algorithm then projects the benign, unknown gamma spectra to this subspace, calculates their MDs, and completes the anomaly detection by comparing these MDs. Monte Carlo simulations and actual tests show that the method is reliable and effective when the subspace has more than 99% of the original information.

关 键 词：Γ能谱 异常识别 人工智能 主成分分析 MAHALANOBIS距离 

分 类 号：TL81[核科学技术—核技术及应用]