Machine learning algorithms are considered as effective methods for improving the effectiveness of neutron-gamma(n-γ)discrimination.This study proposed an intelligent discrimination method that combined a Gaussian mi...Machine learning algorithms are considered as effective methods for improving the effectiveness of neutron-gamma(n-γ)discrimination.This study proposed an intelligent discrimination method that combined a Gaussian mixture model(GMM)with the K-nearest neighbor(KNN)algorithm,referred to as GMM-KNN.First,the unlabeled training and test data were categorized into three energy ranges:0–25 keV,25–100 keV,and 100–2100 keV.Second,GMM-KNN achieved small-batch clustering in three energy intervals with only the tail integral Q_(tail) and total integral Q_(total) as the pulse features.Subsequently,we selected the pulses with a probability greater than 99%from the GMM clustering results to construct the training set.Finally,we improved the KNN algorithm such that GMM-KNN realized the classification and regression algorithms through the LabVIEW language.The outputs of GMM-KNN were the category or regression predictions.The proposed GMM-KNN constructed the training set using unlabeled real pulse data and realized n-γdiscrimination of ^(241)Am-Be pulses using the LabVIEW program.The experimental results demonstrated the high robustness and flexibility of GMM-KNN.Even when using only 1/4 of the training set,the execution time of GMM-KNN was only 2021 ms,with a difference of only 0.13%compared with the results obtained on the full training set.Furthermore,GMM-KNN outperformed the charge comparison method in terms of accuracy,and correctly classified 5.52%of the ambiguous pulses.In addition,the GMM-KNN regressor achieved a higher figure of merit(FOM),with FOM values of 0.877,1.262,and 1.020,corresponding to the three energy ranges,with a 32.08%improvement in 0–25 keV.In conclusion,the GMM-KNN algorithm demonstrates accurate and readily deployable real-time n-γdiscrimination performance,rendering it suitable for on-site analysis.展开更多
Cosmic-ray muons are highly penetrating background-radiation particles found in natural environments.In this study,we develop and test a plastic scintillator muon detector based on machine-learning algorithms.The dete...Cosmic-ray muons are highly penetrating background-radiation particles found in natural environments.In this study,we develop and test a plastic scintillator muon detector based on machine-learning algorithms.The detector underwent muon position-resolution tests at the Institute of Modern Physics in Lanzhou using a multiwire drift chamber(MWDC)experimental platform.In the simulation,the same structural and performance parameters were maintained to ensure the reliability of the simulation results.The Gaussian process regression(GPR)algorithm was used as the position-reconstruction algorithm owing to its optimal performance.The results of the Time Difference of Arrival algorithm were incorporated as one of the features of the GPR model to reconstruct the muon hit positions.The accuracy of the position reconstruction was evaluated by comparing the experimental results with Geant4 simulation results.In the simulation,large-area plastic scintillator detectors achieved a position resolution better than 20 mm.In the experimental-platform tests,the position resolutions of the test detectors were 27.9 mm.We also analyzed factors affecting the position resolution,including the critical angle of the total internal reflection of the photomultiplier tubes and distribution of muons in the MWDC.Simulations were performed to image both large objects and objects with different atomic numbers.The results showed that the system could image high-and low-Z materials in the constructed model and distinguish objects with significant density differences.This study demonstrates the feasibility of the proposed system,thereby providing a new detector system for muon-imaging applications.展开更多
基金supported by National Science Fund for Distinguished Young Scholars of China(No.12205062).
文摘Machine learning algorithms are considered as effective methods for improving the effectiveness of neutron-gamma(n-γ)discrimination.This study proposed an intelligent discrimination method that combined a Gaussian mixture model(GMM)with the K-nearest neighbor(KNN)algorithm,referred to as GMM-KNN.First,the unlabeled training and test data were categorized into three energy ranges:0–25 keV,25–100 keV,and 100–2100 keV.Second,GMM-KNN achieved small-batch clustering in three energy intervals with only the tail integral Q_(tail) and total integral Q_(total) as the pulse features.Subsequently,we selected the pulses with a probability greater than 99%from the GMM clustering results to construct the training set.Finally,we improved the KNN algorithm such that GMM-KNN realized the classification and regression algorithms through the LabVIEW language.The outputs of GMM-KNN were the category or regression predictions.The proposed GMM-KNN constructed the training set using unlabeled real pulse data and realized n-γdiscrimination of ^(241)Am-Be pulses using the LabVIEW program.The experimental results demonstrated the high robustness and flexibility of GMM-KNN.Even when using only 1/4 of the training set,the execution time of GMM-KNN was only 2021 ms,with a difference of only 0.13%compared with the results obtained on the full training set.Furthermore,GMM-KNN outperformed the charge comparison method in terms of accuracy,and correctly classified 5.52%of the ambiguous pulses.In addition,the GMM-KNN regressor achieved a higher figure of merit(FOM),with FOM values of 0.877,1.262,and 1.020,corresponding to the three energy ranges,with a 32.08%improvement in 0–25 keV.In conclusion,the GMM-KNN algorithm demonstrates accurate and readily deployable real-time n-γdiscrimination performance,rendering it suitable for on-site analysis.
基金supported by the National Natural Science Foundation of China(Nos.12275120,11875163)Ministry of Science and Technology of China(No.2020YFE0202001)+1 种基金Science and Technology Innovation Program of Hunan Province(No.2022RC1202)Hunan Provincial Natural Science Foundation(No.2021JJ20006).
文摘Cosmic-ray muons are highly penetrating background-radiation particles found in natural environments.In this study,we develop and test a plastic scintillator muon detector based on machine-learning algorithms.The detector underwent muon position-resolution tests at the Institute of Modern Physics in Lanzhou using a multiwire drift chamber(MWDC)experimental platform.In the simulation,the same structural and performance parameters were maintained to ensure the reliability of the simulation results.The Gaussian process regression(GPR)algorithm was used as the position-reconstruction algorithm owing to its optimal performance.The results of the Time Difference of Arrival algorithm were incorporated as one of the features of the GPR model to reconstruct the muon hit positions.The accuracy of the position reconstruction was evaluated by comparing the experimental results with Geant4 simulation results.In the simulation,large-area plastic scintillator detectors achieved a position resolution better than 20 mm.In the experimental-platform tests,the position resolutions of the test detectors were 27.9 mm.We also analyzed factors affecting the position resolution,including the critical angle of the total internal reflection of the photomultiplier tubes and distribution of muons in the MWDC.Simulations were performed to image both large objects and objects with different atomic numbers.The results showed that the system could image high-and low-Z materials in the constructed model and distinguish objects with significant density differences.This study demonstrates the feasibility of the proposed system,thereby providing a new detector system for muon-imaging applications.
