Convolutional Neural Networks for Challenges in Automated Nuclide Identification

Improvements in Radio-Isotope IDentification (RIID) algorithms have seen a resurgence in interest with the increased accessibility of machine learning models. Convolutional Neural Network (CNN)-based models have been developed to identify arbitrary mixtures of unstable nuclides from gamma spectra. I...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2021-08, Vol.21 (15), p.5238
Main Authors: Turner, Anthony, Wheldon, Carl, Wheldon, Tzany, Gilbert, Mark, Packer, Lee, Burns, Jonathan, Freer, Martin
Format: Article
Language:English
Subjects:
Classification
convolutional neural network
gamma spectrometry
GEANT
Machine learning
Neural networks
nuclear applications
Nuclides
Principal components analysis
radio-isotope identification
Sensors
Shielding
Signal processing
simulations
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Improvements in Radio-Isotope IDentification (RIID) algorithms have seen a resurgence in interest with the increased accessibility of machine learning models. Convolutional Neural Network (CNN)-based models have been developed to identify arbitrary mixtures of unstable nuclides from gamma spectra. In service of this, methods for the simulation and pre-processing of training data were also developed. The implementation of 1D multi-class, multi-label CNNs demonstrated good generalisation to real spectra with poor statistics and significant gain shifts. It is also shown that even basic CNN architectures prove reliable for RIID under the challenging conditions of heavy shielding and close source geometries, and may be extended to generalised solutions for pragmatic RIID.
ISSN:1424-8220
1424-8220
DOI:10.3390/s21155238