Affiliation:
1. Coventry University
2. University of Sheffield AMRC
3. Nissan Technical Centre
4. University of Texas at San Antonio
Abstract
Abstract
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.
Publisher
Research Square Platform LLC
Reference32 articles.
1. Detecting nuclear and radiological materials;The Royal Society;RS policy document,2008
2. Nuclear Security Systems and Measures for Major Public Events;IAEA;IAEA Nucl. Secur. Ser.,2012
3. Database of prompt gamma rays from slow neutron capture for elemental analysis;IAEA,2007
4. Neutron-induced prompt gamma activation analysis (PGAA) of metals and non-metals in ocean floor geothermal vent-generated samples;Perry DL;J. Anal. At. Spectrom.,2002
5. Prompt Gamma Activation Analysis at the Budapest Research Reactor;Belgya T;Phys. Procedia,2012