- 성과
- 논문 (학술지) Untrained neural network-based unfolding method for quantitative analysis of NaI(Tl) gamma spectrometers
| 등록번호 | - |
SCI 구분
※구분 : SCI(SCIE포함), 비SCI
|
SCI |
|---|---|---|---|
| 저자명 (주·공동저자) | 김준혁 ; 고길영; 김호직; 황지성; 송교혁; 조규성 ※ 과제 참여정보와 일치하는 연구자 상세정보로 정확하지 않을 수 있습니다. 동일저자 논문보기 |
||
| 논문구분 | 국외전문학술지 | 학술지명 | Radiation Physics and Chemistry |
| ISSN | 0969-806X | 학술지 출판일자 | 2023-08-01 |
| 학술지 볼륨번호 | 209(110993) | 논문페이지 | 1 ~ 10 |
| 학술지 임팩트팩터 | 2.776 | 기여율 | 100 % |
| DOI | https://doi.org/10.1016/j.radphyschem.2023.110993 | ||
- 초록
- We developed an untrained neural network-based unfolding method (UNU) for both qualitative and quantitative analysis of NaI(Tl) scintillation detectors. Unlike existing deep learning approaches, which commonly rely on a supervised learning strategy, UNU is not required to prepare large numbers of training datasets owing to its scheme of grafting the physical principle of the measured gamma spectrum into the parameter optimizing process within the neural network. We designed a fully connected neural network that receives a measured spectrum as its input and produces a latent fluence spectrum through a series of iterative optimization processes. To verify its performance, we simulated spectra contributed by gamma rays with two or more energies and different relative intensities and measured experimental spectra with different combination of four radioisotopes. For both the simulated and measured spectra, UNU was found to identify the energies of gamma rays and determine their relative intensities with acceptable accuracy. We anticipate that UNU can be developed as a solver for various inverse problems in the field of the radiation measurement.
☞ 성과발생연도 2022년 이후 논문은 조사분석 미확정 정보이며, 조사분석 확정시 기여율 등 일부 정보가 변경될 수 있습니다.
-
※ 연구개발성과 등록 또는 활용에 대한 문의는 논문 연구개발성과 담당자를 통해 문의하시기 바랍니다.
[문의] 한국과학기술정보연구원 Tel : 042)716-7066, https://curation.kisti.re.kr/
※ NTIS 관련 이용문의는 NTIS 콜센터(042-869-1115)로 문의하시기 바랍니다.
