兰州大学机构库
CNN-based event classification of alpha-decay events in nuclear emulsion
Yoshida, J.1,2; Ekawa, H.1; Kasagi, A.1,3; Nakagawa, M.1; Nakazawa, K.3,4; Saito, N.1; Saito, T.R.1,5,6; Taki, M.7; Yoshimoto, M.4
2021-02-11
Source PublicationNuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment   Impact Factor & Quartile
ISSN01689002
EISSN1872-9576
Volume989
page numbers7
AbstractAlpha-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. © 2020 Elsevier B.V.
KeywordConvolutional neural networks Decay (organic) Economic and social effects Emulsification Kinetic energy Kinetics Nuclear reactions Photographic emulsions Statistical tests Thermonuclear reactions Alpha-decay events Discrimination thresholds Event classification Human visual inspection Hyperparameters Nuclear emulsions Precision and recall Standard calibration Convolutionalneuralnetworks Decay(organic) Economicandsocialeffects Kineticenergy Nuclearreactions Photographicemulsions Statisticaltests Thermonuclearreactions Alpha decayevents Discriminationthresholds Eventclassification Humanvisualinspection Nuclearemulsions Precisionandrecall Standardcalibration
PublisherElsevier B.V.
DOI10.1016/j.nima.2020.164930
Indexed ByEI ; SCIE
Language英语
WOS Research AreaInstruments & Instrumentation ; Nuclear Science & Technology ; Physics
WOS SubjectInstruments & Instrumentation ; Nuclear Science & Technology ; Physics, Nuclear ; Physics, Particles & Fields
WOS IDWOS:000611928700021
EI Accession Number20205209685828
EI KeywordsClassification (of information)
EI Classification Number621.2 Fusion Reactors - 716.1 Information Theory and Signal Processing - 742.3 Photographic Materials and Chemicals - 802.2 Chemical Reactions - 802.3 Chemical Operations - 922.2 Mathematical Statistics - 931 Classical Physics ; Quantum Theory ; Relativity - 932.2 Nuclear Physics - 971 Social Sciences ; 621.2 Fusion Reactors ; 716.1 Information Theory and Signal Processing ; 742.3 Photographic Materials and Chemicals ; 802.2 Chemical Reactions ; 802.3 Chemical Operations ; 922.2 Mathematical Statistics ; 931 Classical Physics ; Relativity ; 932.2 Nuclear Physics ; 971 Social Sciences
Original Document TypeJournal article (JA)
Citation statistics
Cited Times:5[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/443930
Collection兰州大学
核科学与技术学院
Corresponding AuthorYoshida, J.
Affiliation
1.High Energy Nuclear Physics Laboratory, Cluster for Pioneering Research, RIKEN, 2-1 Hirosawa, Wako, Saitama; 351-0198, Japan;
2.Department of Physics, Tohoku University, Aramaki, Aoba-ku, Sendai; 980-8578, Japan;
3.Graduate School of Engineering, Gifu University, 1-1 Yanagido, Gifu; 501-1193, Japan;
4.Faculty of Education, Gifu University, 1-1 Yanagido, Gifu; 501-1193, Japan;
5.GSI Helmholtz Centre for Heavy Ion Research, Planckstrasse 1, Darmstadt; D-64291, Germany;
6.School of Nuclear Science and Technology, Lanzhou University, 222 South Tianshui Road, Lanzhou, Gansu Province; 730000, China;
7.Graduate School of Artificial Intelligence and Science, Rikkyo University, 3-34-1 Nishi Ikebukuro, Toshima-ku, Tokyo; 171-8501, Japan
Recommended Citation
GB/T 7714
Yoshida, J.,Ekawa, H.,Kasagi, A.,et al. CNN-based event classification of alpha-decay events in nuclear emulsion[J]. Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment,2021,989.
APA Yoshida, J..,Ekawa, H..,Kasagi, A..,Nakagawa, M..,Nakazawa, K..,...&Yoshimoto, M..(2021).CNN-based event classification of alpha-decay events in nuclear emulsion.Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment,989.
MLA Yoshida, J.,et al."CNN-based event classification of alpha-decay events in nuclear emulsion".Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 989(2021).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Yoshida, J.]'s Articles
[Ekawa, H.]'s Articles
[Kasagi, A.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yoshida, J.]'s Articles
[Ekawa, H.]'s Articles
[Kasagi, A.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yoshida, J.]'s Articles
[Ekawa, H.]'s Articles
[Kasagi, A.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.