Radioisotope identification algorithm using deep artificial neural network for supporting nuclear detection and first response on nuclear security incidents

Kimura, Yoshiki; Tsuchiya, Kenichi*

Radioisotopes, 72(2), p.121 - 139, 2023/07

https://doi.org/10.3769/radioisotopes.72.121

Rapid and precise radioisotope identification in the scene of nuclear detection and nuclear security incidents is one of the challenging issues for the prompt response on the detection alarm or the incidents. A radioisotope identification algorithm using a deep artificial neural network model applicable to handheld gamma-ray detectors has been proposed in the present paper. The proposed algorithm automatically identifies gamma-emitting radioisotopes based on the count contribution ratio (CCR) from each of them estimated by the deep artificial neural network model trained by simulated gamma-ray spectra. The automated radioisotope identification algorithm can support first responders of nuclear detection and nuclear security incidents without sufficient experience and knowledge in radiation measurement. The authors tested the performance of the proposed algorithm using two different types of deep artificial neural network models in application to handheld detectors having high or low energy resolution. The proposed algorithm showed high performance in identifying artificial radioisotopes for actually measured gamma-ray spectra. It was also confirmed that the algorithm is applicable to identifying U and automated uranium categorization by analyzing estimated CCRs by the deep artificial neural network models. The authors also com-pared the performance of the proposed algorithm with a conventional radioisotope identification method and discussed promising ways to improve the performance of the algorithm using the deep artificial neural network.

Optimization of mechanical properties in aluminum alloys hydrogen partitioning control

Toda, Hiroyuki*; Yamaguchi, Masatake; Matsuda, Kenji*; Shimizu, Kazuyuki*; Hirayama, Kyosuke*; Su, H.*; Fujihara, Hiro*; Ebihara, Kenichi; Itakura, Mitsuhiro; Tsuru, Tomohito; et al.

Tetsu To Hagane, 105(2), p.240 - 253, 2019/02

https://doi.org/10.2355/tetsutohagane.TETSU-2018-083

no abstracts in English

Status of JT-60SA tokamak under the EU-JA broader approach agreement

Matsukawa, Makoto; Kikuchi, Mitsuru; Fujii, Tsuneyuki; Fujita, Takaaki; Hayashi, Takao; Higashijima, Satoru; Hosogane, Nobuyuki; Ikeda, Yoshitaka; Ide, Shunsuke; Ishida, Shinichi; et al.

Fusion Engineering and Design, 83(7-9), p.795 - 803, 2008/12

https://doi.org/10.1016/j.fusengdes.2008.06.047

no abstracts in English

Overview of the national centralized tokamak programme

Kikuchi, Mitsuru; Tamai, Hiroshi; Matsukawa, Makoto; Fujita, Takaaki; Takase, Yuichi*; Sakurai, Shinji; Kizu, Kaname; Tsuchiya, Katsuhiko; Kurita, Genichi; Morioka, Atsuhiko; et al.

Nuclear Fusion, 46(3), p.S29 - S38, 2006/03

https://doi.org/10.1088/0029-5515/46/3/S05

The National Centralized Tokamak (NCT) facility program is a domestic research program for advanced tokamak research to succeed JT-60U incorporating Japanese university accomplishments. The mission of NCT is to establish high beta steady-state operation for DEMO and to contribute to ITER. The machine flexibility and mobility is pursued in aspect ratio and shape controllability, feedback control of resistive wall modes, wide current and pressure profile control capability for the demonstration of the high-b steady state.

Design study of national centralized tokamak facility for the demonstration of steady state high- plasma operation

Tamai, Hiroshi; Akiba, Masato; Azechi, Hiroshi*; Fujita, Takaaki; Hamamatsu, Kiyotaka; Hashizume, Hidetoshi*; Hayashi, Nobuhiko; Horiike, Hiroshi*; Hosogane, Nobuyuki; Ichimura, Makoto*; et al.

Nuclear Fusion, 45(12), p.1676 - 1683, 2005/12

https://doi.org/10.1088/0029-5515/45/12/023

Design studies are shown on the National Centralized Tokamak facility. The machine design is carried out to investigate the capability for the flexibility in aspect ratio and shape controllability for the demonstration of the high-beta steady state operation with nation-wide collaboration, in parallel with ITER towards DEMO. Two designs are proposed and assessed with respect to the physics requirements such as confinement, stability, current drive, divertor, and energetic particle confinement. The operation range in the aspect ratio and the plasma shape is widely enhanced in consistent with the sufficient divertor pumping. Evaluations of the plasma performance towards the determination of machine design are presented.

Development of plasma stored energy feedback control and its application to high performance discharges on JT-60U

Oikawa, Toshihiro; Tsuchiya, Katsuhiko; Kurihara, Kenichi; Kawamata, Yoichi; Fukuda, Takeshi*; Fujita, Takaaki; Akasaka, Hiromi; Yonekawa, Izuru; Neyatani, Yuzuru

JAERI-Research 2003-027, 19 Pages, 2003/12

JAERI-Research-2003-027.pdf:1.14MB

no abstracts in English

Study on development of a geological disposal technology integration system

Ishihara, Yoshinao*; Matsuoka, Fushiki*; Sagawa, Hiroshi*; Kawahara, Kenichi*; Kataoka, Shinichi*; Shinohara, Yoshinori*; Muroi, Masayuki*; Tsuchiya, Makoto*; Tsujimoto, Keiichi*; Ohashi, Toyo*

JNC TJ8400 2001-011, 259 Pages, 2001/03

JNC-TJ8400-2001-011.pdf:0.99MB

In this study, the basic design study on integrated computer system has been carried out in order to develop the integrated methodologies for future research and development activities of geological disposal system. The key conclusions are summarized as follows: (1) As the result of the investigation of work items and associated flow of information (data) between items in the second progress report by JNC, the interaction matrix and work flow chart have been identified in order to specify the basic configuration of the integrated computer system. In addition, the model chain and the structure of data relation between the repository design study and safety assessment study have been summarized. (2)We organized and examined the system factor and the information process flow in the design, safety analysis, and geological environment study based on the 2000 Report by JNC. Then we analyzed the workflow of geological disposal business when a specific site for a repository is fixed to obtain the system factor and the information process flow. We consider the fracture/porous media, site location (land/under the sea), and long-term stability of the crust (upheaval/sink) as the key factors in examining the workflow of geological disposal business. Then we organized the information change between the design and other study in geological disposal based on the 2000 Report by JNC. We examined the ideal workflow in which the design, safety analysis, and geologic environment study of geological disposal are closely coupled. We examined the scientific and technical base of the knowledge base (the system factor and the information process flow) which is derived from the above to construct the hierarchical structure of the knowledge base for geological disposal. (3)As the result of the interaction matrix and work flow chart for the R&D activities, the conceptual design and the function diagram on the integrated computer system has been proposed. (4)We examined the plan to ...

Machine-learning based gamma-ray spectrum analysis for initial response on nuclear security event; Development of training data set by detector simulation and usability evaluation for radioisotope identification algorism

Kimura, Yoshiki; Tsuchiya, Kenichi*

no journal, , 

A nuclear security event involving nuclear and other radioactive materials out of regulatory control (MORC) has potential severe consequence on public health, environments, economics and society. When a nuclear security event caused by MORC would be occurred, it is essential to identify the hazardous substances such as nuclear materials and radioisotopes as the initial response activity at the event scene. In this study, automated radioisotope identification algorism by Machine-Learning (ML) based gamma-ray spectrum analysis using handheld type detectors have been developed. The training data set for ML-based algorism has been developed based on detector simulation and the usability of the simulation-based data set for ML model training to perform radioisotope identification has been discussed.

Development of radioisotope identification algorism based on deep neural network model for supporting first response on nuclear security incidents

Kimura, Yoshiki; Tsuchiya, Kenichi*

no journal, , 

no abstracts in English