CNN-based event classification of alpha-decay events in nuclear emulsion

CNN-based event classification of alpha-decay events in nuclear emulsion
复制标题

基于 CNN 的核乳剂中 α 衰变事件的事件分类

DOI:
10.1016/j.nima.2020.164930
复制
发表时间:
2020
期刊:
Nuclear Instruments and Methods in Physics Research A
影响因子:
--
通讯作者:
et al.
et al.
中科院分区:
--
文献类型:
--
作者:
J. Yoshida;K. Nakazawa;et al.

文献摘要

参考文献

被引文献

相似文献

核乳胶中的α衰变事件是每个乳胶片中径迹长度和动能之间关系的标准校准源。我们开发了一个有效的分类器,使用卷积神经网络(CNN)对乳液中各种顶点状物体的α衰变事件进行分类。我们使用15885张顶点类对象的图像训练了CNN,其中包括906个α衰变事件,并使用46948张图像的数据集进行了测试,其中包括255个α衰变事件。对于相同的数据集,使用先前的方法而不使用CNN的分类的精确度和召回率得分分别为0.081 ± 0.006和0.788 ± 0.056。相比之下,我们训练的模型在广泛调整CNN的超参数后,测试数据集的平均精度得分为0.760 ± 0.006。此外,对于所获得的模型,分类的区分阈值可以根据精确度和召回率之间的权衡任意调整。此外,开发的分类器获得了准确率为0.571 ± 0.017时,召回分数被分配的值为0.788。最后,与没有CNN的前一种方法相比,开发的CNN方法减少了分类后所需的额外人类视觉检查的需要,减少了约1/7,证明了所提出的分类器的可行性。
Alpha-decay events in a nuclear emulsion are standard calibration sources for the relation between the track length and the kinetic energy in each emulsion sheet. We developed an efficient classifier that sorts such alpha-decay events from various vertex-like objects in an emulsion using a convolutional neural network (CNN). We trained the CNN using 15885 images of vertex-like objects, including 906 alpha-decay events, and tested it using a dataset of 46948 images including 255 alpha-decay events. The precision and recall scores of the classification using the previous method without a CNN for the same dataset were 0.081 ± 0.006 and 0.788 ± 0.056, respectively. In contrast, our trained models achieved an average precision score of 0.760 ± 0.006 for the test dataset, after extensively tuning the hyperparameters of the CNN. Moreover, for the model obtained, the discrimination threshold of the classification can be adjusted arbitrarily according to the trade-off between the precision and recall scores. Furthermore, the developed classifier obtained a precision of 0.571 ± 0.017 when the recall score was assigned a value of 0.788. Finally, the developed CNN method reduced the need for additional human visual inspection, required after classification, by a factor of approximately 1/7, compared to the former method without a CNN, proving the feasibility of the proposed classifier.
一种新的α衰变事件扫描系统,作为核乳剂中距离-能量关系的校准源
DOI: 10.1016/j.nima.2016.11.044
发表时间: 2017
期刊: Nuclear Instruments and Methods in Physics Research A
影响因子: --
作者:
J.Yoshida;S.Kinbara;A.Mishina;K.Nakazawa;M.K.Soe;A.M.M.Theint;K.T.Thint
通讯作者: K.T.Thint
使用 (R)-BINOL-6,6-二羧酸合成新型手性 Zn-MOF 并使用填充其的 HPLC 柱分离对映体
DOI: --
发表时间: 2015
期刊:
影响因子: --
作者:
T. Yano;M. Goto;N. Tamai;H. Matsuki;大坪 泰洋・田中 耕一
通讯作者: 大坪 泰洋・田中 耕一
DOI: 10.1016/j.nima.2016.12.046
发表时间: 2017
期刊: Nuclear Instruments and Methods in Physics Research A
影响因子: --
作者:
M.K.Soe;R.Goto;A.Mishina;Y.Nakanisi;D.Nakashima;J.Yoshida;K.Nakazawa
通讯作者: K.Nakazawa
DOI: 10.1016/j.epsl.2007.09.001
发表时间: 2007-11-15
影响因子: 5.3
作者:
Tanaka, Hiroyuki K. M.;Nakano, Toshiyuki;Niwa, Kimio
通讯作者: Niwa, Kimio
DOI: --
发表时间: 2003
期刊: Proceedings of 2^<nd> Asia Pacific Conference on Few-Body Problems in Physics ; (ed.by H.Q.Song et al.) Modern Physics Lett. A18
影响因子: --
作者:
K.Nakazawa;BNL-E964 collaborators.
通讯作者: BNL-E964 collaborators.