Lost gamma source detection algorithm based on convolutional neural network

Fathi, Atefeh; Masoudi, S. Farhad

doi:10.1016/j.net.2021.05.016

Cited by 12 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[13] Fathi et al used the results of Geant4 simulations to train convolutional neural networks to propose a new method for gamma source detection. [14] Daniel et al used Geant4 to perform Monte Carlo simulations to obtain a database to propose convolutional neural networks based automatic identification method as a new tool for real-time analysis of gamma-ray spectra. [15] In this paper, we propose a fast modeling method based on dense convolutional networks (DenseNets) [16] for SEEs.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Linear Energy Transfer Based on Geant4 Simulation and Neural Networks

Zhang

Chen

Liu

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

Most of the traditional studies based on single event effects (SEEs) favor the analysis of electrical mechanisms of semiconductor devices. Professional simulation software in microelectronics requires researchers to have a solid knowledge of microelectronics theory, and the modeling threshold of the software is relatively high, the simulation speed is slow, and accurate simulation of inter‐particle and particle–material interactions is lacking. SEEs are related to linear energy transfer (LET), in this paper, a method is proposed to obtain LET datas to predict SEEs of particles incident on silicon materials by using the Geant4 Monte Carlo toolkit in combination with a dense convolutional network to accurately and rapidly estimate the energy deposition characteristics of the particles. The proposed network structure has a high prediction accuracy with a mean square error （MSE） of only 1.77 × 10−4. Compared with Geant4, which takes 1 min to compute a set of data, the proposed network structure takes only 0.0817 s. The method explores the feasibility of using Geant4 to model semiconductor devices combined with deep learning algorithms, providing a new research perspective for the prediction of microelectronic devices and making it possible to explore the influence of integrated circuits by SEEs.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Linear Energy Transfer Based on Geant4 Simulation and Neural Networks

Zhang

Chen

Liu

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

show abstract

“…In recent years, artificial intelligence (AI)-based methods such as artificial neural networks (ANN) and machine learning have been widely applied in many different areas, including nuclear physics for optimization purposes 24 – 30 .…”

Section: Introductionmentioning

confidence: 99%

Thermal neutron beam optimization for PGNAA applications using Q-learning algorithm and neural network

Zolfaghari

Masoudi

Rahmani

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

As a powerful, non-destructive analysis tool based on thermal neutron capture reaction, prompt gamma neutron activation analysis (PGNAA) indeed requires the appropriate neutron source. Neutrons produced by electron Linac-based neutron sources should be thermalized to be appropriate for PGNAA. As a result, thermalization devices (TDs) are used for the usual fast neutron beam to simultaneously maximize the thermal neutron flux and minimize the non- thermal neutron flux at the beam port of TD. To achieve the desired thermal neutron flux, the optimized geometry of TD including the proper materials for moderators and collimator, as well as the optimized dimensions are required. In this context, TD optimization using only Monte Carlo approaches such as MCNP is a multi-parameter problem and time-consuming task. In this work, multilayer perceptron (MLP) neural network has been applied in combination with Q-learning algorithm to optimize the geometry of TD containing collimator and two moderators. Using MLP, both thickness and diameter of the collimator at the beam port of TD have first been optimized for different input electron energies of Linac as well as for moderators’ thickness values and the collimator. Then, the MLP has been learned by the thermal and non-thermal neutron flux simultaneously at the beam port of TD calculated by MCNPX2.6 code. After selecting the optimized geometry of the collimator, a combination of Q-learning algorithm and MLP artificial neural network have been used to find the optimal moderators’ thickness for different input electron energies of Linac. Results verify that the final optimum setup can be obtained based on the prepared dataset in a considerably smaller number of simulations compared to conventional calculation methods as implemented in MCNP.

show abstract

“…The algorithmic multirobot gas source localization method has higher accuracy. Fathi et al [6] have developed an indoor radioactive source localization algorithm based on convolutional neural network algorithm. The localization parameters were optimized by the neural network algorithm, the location of the source can be identified with a certain accuracy without human intervention.…”

Section: Introductionmentioning

confidence: 99%

Rapid localization of radioactive leaks based on hybrid adaptive grey wolf algorithm

Zhao

Liu²,

Zhang³

et al. 2022

J. Inst.

View full text Add to dashboard Cite

Radioactive source localization algorithms have been widely used in the detection of nuclear accident areas. But some shortcomings, such as complex algorithm structure, slow localization speed and poor accuracy, were obviously performed to affect mobile robot locating autonomously. In this paper, a potential alternative method was investigated to be a new usage of locating leaks, just via specifying the change of exposure rate. In this model, several key factors, such as gamma ray attenuation, scattering factor, travel angle guide, spatial discretization, etc., were taken into consideration, to demonstrate the effectiveness of the algorithm, which is appropriated in unknown areas of the radioactive waste repository. Since there are three factors with different contribution, such as position, quantity of the source and gamma ray energy, which considered to demonstrate its impact on success. So, a hybrid adaptive grey wolf algorithm (HAGWO) has been adopted and implemented to develop a novel rapid method of radioactive leak location. Three aspects, including the good point set initialization in population size, balanced convergence function, and self-adaptive greedy strategy for population update, were optimized and merged into the locating model. To investigate the effectiveness of the algorithm, results of HAGWO are compared with grey wolf algorithm (GWO), good point set initialization strategy GWO(GGWO) and adaptive head wolf strategy GWO (ALGWO) in convergence speed, accuracy, stability and positioning error of single and double leak points. It is observed that convergence speed is increased by 37.93 ± 2% at the highest; the convergence accuracy is increased by 92.42 ± 2% at the most; the stability is improved by 30% ∼ 50%. The positioning error of single leak point is within 1.08%, and the positioning error of double leak point is less than 8.90%. Besides, compared with GWO, GGWO and ALGWO, the single-point accuracy is improved by 1.36 percentage points (to GWO), and the double-point accuracy is improved by 40.35 percentage points (to ALGWO) at most. It is observed that HAGWO performs the best in locating leaks, with a faster convergence, stronger stability and more accuracy.

show abstract

Lost gamma source detection algorithm based on convolutional neural network

Cited by 12 publications

References 25 publications

Prediction of Linear Energy Transfer Based on Geant4 Simulation and Neural Networks

Prediction of Linear Energy Transfer Based on Geant4 Simulation and Neural Networks

Thermal neutron beam optimization for PGNAA applications using Q-learning algorithm and neural network

Rapid localization of radioactive leaks based on hybrid adaptive grey wolf algorithm

Contact Info

Product

Resources

About