Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN

Zihang Lin; Rongrong Guo; Zhuochen Cai; Xianggang Zhang; Shixuan Guo; Yijun Cai; Huixiang Huang; Tao Wang

doi:10.1117/12.3058837

Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN

Zihang Lin, Rongrong Guo, Zhuochen Cai, Xianggang Zhang, Shixuan Guo, Yijun Cai, Huixiang Huang, Tao Wang

School of Materials Sience and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The generation of neutrons always comes with accompanying gamma rays. Therefore, it is necessary to eliminate the influence of gamma rays in neutron measurement and discriminate n-γ rays. The Cs2LiLaBr6 (CLLB) crystal is capable of detecting both neutrons and gamma rays and has excellent scintillation performance. To enhance its discriminating capabilities, this study suggests combining CLLB crystals with a convolutional neural network (CNN) and principal component analysis (PCA). The CNN is used to extract features of neutron and gamma rays, and then the PCA method automatically selects the fewest principal components with at least 95% variance, enabling effective n-γ discriminating. Experimental results demonstrate that the PCA-CNN model proposed in this study outperforms the CNN alone, achieving a discriminating accuracy of 99.07%.

Original language	English
Title of host publication	International Conference on Optoelectronic Materials and Devices, ICOMD 2024
Editors	Tingchao He, Ching Yern Chee
Publisher	SPIE
ISBN (Electronic)	9781510689039
DOIs	https://doi.org/10.1117/12.3058837
State	Published - 2025
Event	2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024 - Chongqing, China Duration: 22 Nov 2024 → 24 Nov 2024

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13549
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024
Country/Territory	China
City	Chongqing
Period	22/11/24 → 24/11/24

Keywords

CNN
inorganic scintillation detector
n-γ discrimination
PCA

Access to Document

10.1117/12.3058837

Cite this

Lin, Z., Guo, R., Cai, Z., Zhang, X., Guo, S., Cai, Y., Huang, H., & Wang, T. (2025). Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN. In T. He, & C. Y. Chee (Eds.), International Conference on Optoelectronic Materials and Devices, ICOMD 2024 Article 1354913 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13549). SPIE. https://doi.org/10.1117/12.3058837

@inproceedings{ce89094b5b9843f88b7447eea6a10f6d,

title = "Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN",

abstract = "The generation of neutrons always comes with accompanying gamma rays. Therefore, it is necessary to eliminate the influence of gamma rays in neutron measurement and discriminate n-γ rays. The Cs2LiLaBr6 (CLLB) crystal is capable of detecting both neutrons and gamma rays and has excellent scintillation performance. To enhance its discriminating capabilities, this study suggests combining CLLB crystals with a convolutional neural network (CNN) and principal component analysis (PCA). The CNN is used to extract features of neutron and gamma rays, and then the PCA method automatically selects the fewest principal components with at least 95% variance, enabling effective n-γ discriminating. Experimental results demonstrate that the PCA-CNN model proposed in this study outperforms the CNN alone, achieving a discriminating accuracy of 99.07%.",

keywords = "CNN, inorganic scintillation detector, n-γ discrimination, PCA",

author = "Zihang Lin and Rongrong Guo and Zhuochen Cai and Xianggang Zhang and Shixuan Guo and Yijun Cai and Huixiang Huang and Tao Wang",

note = "Publisher Copyright: {\textcopyright} 2025 SPIE.; 2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024 ; Conference date: 22-11-2024 Through 24-11-2024",

year = "2025",

doi = "10.1117/12.3058837",

language = "英语",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Tingchao He and Chee, {Ching Yern}",

booktitle = "International Conference on Optoelectronic Materials and Devices, ICOMD 2024",

}

Lin, Z, Guo, R, Cai, Z, Zhang, X, Guo, S, Cai, Y, Huang, H & Wang, T 2025, Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN. in T He & CY Chee (eds), International Conference on Optoelectronic Materials and Devices, ICOMD 2024., 1354913, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13549, SPIE, 2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024, Chongqing, China, 22/11/24. https://doi.org/10.1117/12.3058837

Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN. / Lin, Zihang; Guo, Rongrong; Cai, Zhuochen et al.
International Conference on Optoelectronic Materials and Devices, ICOMD 2024. ed. / Tingchao He; Ching Yern Chee. SPIE, 2025. 1354913 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13549).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN

AU - Lin, Zihang

AU - Guo, Rongrong

AU - Cai, Zhuochen

AU - Zhang, Xianggang

AU - Guo, Shixuan

AU - Cai, Yijun

AU - Huang, Huixiang

AU - Wang, Tao

PY - 2025

Y1 - 2025

N2 - The generation of neutrons always comes with accompanying gamma rays. Therefore, it is necessary to eliminate the influence of gamma rays in neutron measurement and discriminate n-γ rays. The Cs2LiLaBr6 (CLLB) crystal is capable of detecting both neutrons and gamma rays and has excellent scintillation performance. To enhance its discriminating capabilities, this study suggests combining CLLB crystals with a convolutional neural network (CNN) and principal component analysis (PCA). The CNN is used to extract features of neutron and gamma rays, and then the PCA method automatically selects the fewest principal components with at least 95% variance, enabling effective n-γ discriminating. Experimental results demonstrate that the PCA-CNN model proposed in this study outperforms the CNN alone, achieving a discriminating accuracy of 99.07%.

AB - The generation of neutrons always comes with accompanying gamma rays. Therefore, it is necessary to eliminate the influence of gamma rays in neutron measurement and discriminate n-γ rays. The Cs2LiLaBr6 (CLLB) crystal is capable of detecting both neutrons and gamma rays and has excellent scintillation performance. To enhance its discriminating capabilities, this study suggests combining CLLB crystals with a convolutional neural network (CNN) and principal component analysis (PCA). The CNN is used to extract features of neutron and gamma rays, and then the PCA method automatically selects the fewest principal components with at least 95% variance, enabling effective n-γ discriminating. Experimental results demonstrate that the PCA-CNN model proposed in this study outperforms the CNN alone, achieving a discriminating accuracy of 99.07%.

KW - CNN

KW - inorganic scintillation detector

KW - n-γ discrimination

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=105001673687&partnerID=8YFLogxK

U2 - 10.1117/12.3058837

DO - 10.1117/12.3058837

M3 - 会议稿件

AN - SCOPUS:105001673687

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Conference on Optoelectronic Materials and Devices, ICOMD 2024

A2 - He, Tingchao

A2 - Chee, Ching Yern

PB - SPIE

T2 - 2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024

Y2 - 22 November 2024 through 24 November 2024

ER -

Research on n - γ Identification of Scintillation Neutron Detector Using PCA-CNN

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this