Nuclear Science and Techniques

《核技术》(英文版) ISSN 1001-8042 CN 31-1559/TL     2019 Impact factor 1.556

Nuclear Science and Techniques ›› 2018, Vol. 29 ›› Issue (5): 69 doi: 10.1007/s41365-018-0402-4

• NUCLEAR ELECTRONICS AND INSTRUMENTATION • Previous Articles     Next Articles

Spectrometry analysis based on approximation coefficients and deep belief networks

Jian-Ping He 1 • Xiao-Bin Tang 1,2 • Pin Gong 1  • Peng Wang 1 • Zhen-Yang Han 1 • Wen Yan 1 • Le Gao 1   

  1. 1 Department of Nuclear Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
    2 Jiangsu Key Laboratory of Nuclear Energy Equipment Materials Engineering, Nanjing 210016, China
  • Contact: Xiao-Bin Tang E-mail:tangxiaobin@nuaa.edu.cn
  • Supported by:

    This work was supported by the National Natural Science Foundation of China (No. 11675078), the Foundation of Graduate Innovation Center in NUAA (No. kfjj20160606, kfjj20170613, and kfjj20170617) and the Fundamental Research Funds for the Central Universities, the Primary Research and Development Plan of Jiangsu Province (No. BE2017729), the Fundamental Research Funds for the Central Universities (No. NJ20160034), the Funding of Jiangsu Innovation Program for Graduate Education (No. KYLX16_0353) and the Fundamental Research Funds for the Central Universities, and the Priority Academic Program Development of Jiangsu Higher Education Institutions.

PDF ShareIt Export Citation
Jian-Ping He, Xiao-Bin Tang, Pin Gong, Peng Wang, Zhen-Yang Han, Wen Yan, Le Gao. Spectrometry analysis based on approximation coefficients and deep belief networks.Nuclear Science and Techniques, 2018, 29(5): 69     doi: 10.1007/s41365-018-0402-4
Citations
Altmetrics

Abstract:

A method of spectrometry analysis based on approximation coefficients and deep belief networks was developed. Detection rate and accurate radionuclide identification distance were used to evaluate the performance of the proposed method in identifying radionuclides. Experimental results show that identification performance was not affected by detection time, number of radionuclides, or detection distance when the minimum detectable activity of a single radionuclide was satisfied. Moreover, the proposed method could accurately predict isotopic compositions from the spectra of moving radionuclides. Thus, the designed method can be used for radiation monitoring instruments that identify radionuclides.

Key words: Approximation coefficient, Deep belief network, Spectrometry analysis, Radionuclide identification, Detection rate