Matrix effects corrections in prompt gamma-ray spectra of a PGNAA online analyzer system using artificial neural network

Shahabinejad, H.; Vosoughi, Naser; Saheli, Fereshte

doi:10.1016/j.pnucene.2019.103146

Cited by 14 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resolution of the detector was also taken into account in the simulations by considering the energy resolution (FWHM) of the HPGe detector measured in the experiments. The broadening method of the MCNP Monte Carlo code [4,50,51] was used to propagate the energy resolution measured experimentally into the output of the Geant4 simulations. In this method, the deposited energy of each event in the detector (𝐸 0 ) is broadened by sampling from a Gaussian function whose mean value is 𝐸 0 and the standard deviation is fitted from the experimental data as it will be reported in the results section.…”

Section: Monte Carlo Simulationsmentioning

confidence: 99%

“…High precision gamma-ray spectroscopy is a powerful tool that is widely used to study the structure of excited nuclear states [1,2] of irradiated targets in many applications such as prompt gamma neutron activation analysis [3][4][5] and proton induced prompt gamma emission [6][7][8][9]. The prompt gammarays produced by nuclear interactions between the target and the incident particles can be used for the determination and online monitoring of the elemental composition of the irradiated target.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation the nonlinear response function of a HPGe detector for 59 keV to 10.7 MeV gamma-rays using a Monte Carlo simulation and comparison with experimental data

Saheli¹,

Riazi²,

Jokar³

et al. 2021

J. Inst.

View full text Add to dashboard Cite

A: Modeling of High Purity Germanium (HPGe) detector on a wide energy range is important in gamma-ray spectroscopy. The precisely modeled detector can be used for protoninduced prompt gamma-ray spectroscopy. In this work, we used both the gamma-rays of calibration sources and prompt gamma-rays emitted in proton capture reactions to model a coaxial p-type HPGe detector using Geant4 Monte Carlo simulation for the gamma-ray energy range of 59-10764 keV. The calibration sources were 137 Cs, 241 Am, 60 Co, 152 Eu, and 133 Ba, while the prompt gamma-rays were due to the gamma-ray cascades following the 27 Al(p,𝛾) 28 Si reaction capture at the resonant energies of 992, 1317 and 2483 keV, as well as the 23 Na(p,𝛾) 24 Mg reaction capture at the resonant energies of 1417 and 1395 keV. According to the results obtained, the presented simulated and experimental spectra show a good agreement. In addition, the mean and maximum relative deviations between experimental and simulated efficiencies corresponding to 27 major peaks are smaller than 5% and 15%, respectively. K: Gamma detectors (scintillators, CZT, HPGe, HgI etc); Simulation methods and programs; Detector modelling and simulations I (interaction of radiation with matter, interaction of photons with matter, interaction of hadrons with matter, etc); Accelerator Applications

show abstract

Section: Monte Carlo Simulationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation the nonlinear response function of a HPGe detector for 59 keV to 10.7 MeV gamma-rays using a Monte Carlo simulation and comparison with experimental data

Saheli¹,

Riazi²,

Jokar³

et al. 2021

J. Inst.

View full text Add to dashboard Cite

show abstract

“…The knowledge information available in the predictor variables is transferred from the input neurons to the hidden neurons via the weight, and then summed to get an estimate of the total stimulus of each hidden unit (Ozonoh et al 2020). The hidden neurons send the collected information to the output neuron through an activation function, generally the sigmoid (Shahabinejad et al 2020). Finally, the output neuron provides a response, then, compared to the desired value, and the error expected is calculated.…”

Section: Multilayer Perceptron Artificial Neural Network (Mlpnn)mentioning

confidence: 99%

Modelling Reference Evapotranspiration using a Novel Regression-based Method: Radial basis M5 Model Tree

Kişi

Keshtegar

Zounemat‐Kermani

et al. 2021

Preprint

View full text Add to dashboard Cite

In the current study, an ability of a novel regression-based method is evaluated in modelling daily reference evapotranspiration (ET0), which is an important issue in water resources management plans and helps farmers in irrigation planning. The method was developed by hybridizing radial basis function and M5 model tree and called as radial basis M5 model tree (RM5Tree). The radial-based kernel function was used to control the input variables in modelling process of M5 model tree. The new model results were compared with traditional M5 model tree (M5Tree), response surface method (RSM) and two neural networks (multi-layer perceptron neural networks, MLPNN & radial basis function neural network, RBFNN) with respect to several statistical indices. Daily climatic data (relative humidity, RH, solar radiation, SR, wind speed, air temperature, T) recorded at three stations in Turkey, Mediterranean Region, were used. The effect of each weather data on ET0 was also investigated by utilizing three different input scenarios with various combinations of input variables. On the whole, the RM5Tree provided the best results (NSE > 0.997) followed by the MLPNN (NSE > 0.990), and M5Tree (NSE > 0.945) in modelling daily ET0. The SR was observed as the most effective input parameter on ET0 which was followed by the T and RH. However, the findings of the third modelling scenario revealed that taking into account of all variables would considerably increase models’ accuracies for the three stations.

show abstract

“…Sullivan et al [13] and Kamuda et al [14,15] presented an automated isotope algorithm in a large dataset of low-resolution gamma ray spectra containing a mixture of multiple radio-isotopes based on Bayesian and artificial neural networks respectively. Specifically, PGAA data have been analysed via applying machine-learning methods for detection of illicit materials [16,17] and online monitoring [18]. Recently, Kamuda et al [19] compared the performance of artificial neural networks and convolutional neural networks for automated gamma-ray spectroscopy to identify mixtures of radioisotopes.…”

Section: Introductionmentioning

confidence: 99%

A comparison of machine learning methods to classify radioactive elements using prompt-gamma-ray neutron activation data

Mathew

Kshirsagar

Abidin

et al. 2023

Preprint

View full text Add to dashboard Cite

The detection of illicit radiological materials is critical to establishing a robust second line of defence in nuclear security. Neutron-capture prompt-gamma activation analysis (PGAA) can be used to detect multiple radioactive materials across the entire Periodic Table. However, long detection times and a high rate of false positives pose a significant hindrance in the deployment of PGAA-based systems to identify the presence of illicit substances in nuclear forensics. In the present work, six different machine-learning algorithms were developed to classify radioactive elements based on the PGAA energy spectra. The model performance was evaluated using standard classification metrics and trend curves with an emphasis on comparing the effectiveness of algorithms that are best suited for classifying imbalanced datasets. We analyse the classification performance based on Precision, Recall, F1-score, Specificity, Confusion matrix, ROC-AUC curves, and Geometric Mean Score (GMS) measures. The tree-based algorithms (Decision Trees, Random Forest and AdaBoost) have consistently outperformed Support Vector Machine and K-Nearest Neighbours. Based on the results presented, AdaBoost is the preferred classifier to analyse data containing PGAA spectral information due to the high recall and minimal false negatives reported in the minority class.

show abstract

Matrix effects corrections in prompt gamma-ray spectra of a PGNAA online analyzer system using artificial neural network

Cited by 14 publications

References 27 publications

Evaluation the nonlinear response function of a HPGe detector for 59 keV to 10.7 MeV gamma-rays using a Monte Carlo simulation and comparison with experimental data

Evaluation the nonlinear response function of a HPGe detector for 59 keV to 10.7 MeV gamma-rays using a Monte Carlo simulation and comparison with experimental data

Modelling Reference Evapotranspiration using a Novel Regression-based Method: Radial basis M5 Model Tree

A comparison of machine learning methods to classify radioactive elements using prompt-gamma-ray neutron activation data

Contact Info

Product

Resources

About