Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Kimura, Yoshiki; Tsuchiya, Kenichi*
Radioisotopes, 72(2), p.121 - 139, 2023/07
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.
Sasaki, Miyuki; Sanada, Yukihisa
Journal of Advanced Simulation in Science and Engineering (Internet), 9(1), p.30 - 39, 2022/01
This study presents the evaluation results of the validity of the visualization map of the ambient dose rate at 1 m above the ground level using an artificial neural network. The dose rate map created using the artificial neural network-based method is found to reproduce ground-based survey results better than conventional methods. Suggested to improve the validity of the airborne radiation survey visualization, applying the color data obtained using a photogrammetry system is a new experience.
Sasaki, Miyuki; Sanada, Yukihisa; Katengeza, E. W.*; Yamamoto, Akio*
Scientific Reports (Internet), 11, p.1857_1 - 1857_11, 2021/01
Times Cited Count：13 Percentile：68.64(Multidisciplinary Sciences)This study proposed a new method to visualize the ambient dose rate distribution using artificial neural networks from the results of airborne radiation monitoring. The method used airborne radiation monitoring conducted around Fukushima Daiichi Nuclear Power Plant by an unmanned aerial vehicle. A lot of survey data which had obtained in the past was used as training data for building a network. The reliability of the artificial neural network method was evaluated by comparison with the ground-based survey data. The dose rate map that was created by the artificial neural networks method reproduced the ground-based survey results better than traditional methods.
