期刊
出版社
ELSEVIER
DOI: 10.1016/j.nima.2014.12.087
关键词
Support vector machine; n/gamma Discrimination; The moment analysis method; Charge comparison method
类别
资金
- National Natural Science Foundation of China [10935005, 10945002, 11275134]
In this study, the combination of the support vector machine (SVM) method with the moment analysis method (MAM) is proposed and utilized to perform neutron/gamma (n/gamma) discrimination of the pulses from an organic liquid scintillator (OLS). Neutron and gamma events, which can be firmly separated on the scatter plot drawn by the charge comparison method (CCM), are detected to form the training data set and the test data set for the SVM, and the MAM is used to create the feature vectors for individual events in the data sets. Compared to the traditional methods, such as CCM, the proposed method can not only discriminate the neutron and gamma signals, even at lower energy levels, but also provide the corresponding classification accuracy for each event, which is useful in validating the discrimination. Meanwhile, the proposed method can also offer a predication of the classification for the under-energy-limit events. (C) 2014 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据