Abstract
Prompt Gamma Neutron Activation Analysis is a nuclear-based technique that can be used in explosives detection. It relies on bombarding unknown samples with neutrons emitted from a neutron source. These neutrons interact with the sample nuclei emitting the gamma spectrum with peaks at specific energies, which are considered a fingerprint for the sample composition. Analyzing these peaks heights will give information about the unknown sample material composition. Shielding the sample from gamma rays or neutrons will affect the gamma spectrum obtained to be analyzed, providing a false indication about the sample constituents, especially when the shield is unknown. Here we show how using deep neural networks can solve the shielding drawback associated with the prompt gamma neutron activation analysis technique in explosives detection. We found that the introduced end-to-end framework was capable of differentiating between explosive and non-explosive hydrocarbons with accuracy of 95% for the previously included explosives in the model development data set. It was also, capable of generalizing with accuracy 80% over the explosives which were not included in the model development data set. Our results show that coupling prompt gamma neutron activation analysis with deep neural networks has a good potential for high accuracy explosives detection regardless of the shield presence.
Highlights
Prompt Gamma Neutron Activation Analysis is a nuclear-based technique that can be used in explosives detection
Multilayer perceptron models (MLPs) from the artificial neural networks (ANNs) family of artificial intelligence was coupled with pulsed fast thermal neutron activation (PFTNA) technique for detecting e xplosives[12]
The pipeline was capable of detecting minimum mass of 708 g of pentaerythritol tetranitrate (PETN) for the shields water, borated water, iron, lead, and boron
Summary
Due to the sensitivity of the research topic, we used synthesized data instead of experimental data. Using detectors array in PGNAA setups is a standard procedure for detecting the emitted gamma spectrum. Average standard deviation scores associated with the generated data are listed in Supplementary Table 5. In this proof of concept, the obtained gamma spectrum is per source neutron and per second. In practice assuming 10% of the baggage are suspicious and using a high-intensity neutron generator This will reduce the time of the multibarrier screening process and ensure an efficient detection of both shielded and unshielded illicit materials. The presence of the X-ray prescreening device will help to direct the neutron generator specific to locations in the parcel and reduce the time for the second screening p rocess[23]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
