Convolutional Neural Networks for Challenges in Automated Nuclide Identification.
Anthony N TurnerCarl WheldonTzany Kokalova WheldonMark R GilbertLee W PackerJonathan BurnsMartin FreerPublished in: Sensors (Basel, Switzerland) (2021)
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.
Keyphrases
- convolutional neural network
- deep learning
- machine learning
- artificial intelligence
- big data
- healthcare
- bioinformatics analysis
- primary care
- virtual reality
- mental health
- density functional theory
- quality improvement
- high throughput
- clinical trial
- study protocol
- ionic liquid
- electronic health record
- single cell
- mass spectrometry
- data analysis
- gas chromatography