IMPROVEMENT OF DOSE ESTIMATION PROCESS USING ARTIFICIAL NEURAL NETWORKS

Gal Amit; Hanan Datz

doi:10.1093/rpd/ncy185

IMPROVEMENT OF DOSE ESTIMATION PROCESS USING ARTIFICIAL NEURAL NETWORKS

Radiat Prot Dosimetry. 2019 Jul 1;184(1):36-43. doi: 10.1093/rpd/ncy185.

Authors

Gal Amit¹, Hanan Datz¹

Affiliation

¹ Radiation Safety Division, Soreq Nuclear Research Center, Yavne, Israel.

PMID: 30371863
DOI: 10.1093/rpd/ncy185

Abstract

We present here for the first time a fast and reliable automatic algorithm based on artificial neural networks for the anomaly detection of a thermoluminescence dosemeter (TLD) glow curves (GCs), and compare its performance with formerly developed support vector machine method. The GC shape of TLD depends on numerous physical parameters, which may significantly affect it. When integrated into a dosimetry laboratory, this automatic algorithm can classify 'anomalous' (having any kind of anomaly) GCs for manual review, and 'regular' (acceptable) GCs for automatic analysis. The new algorithm performance is then compared with two kinds of formerly developed support vector machine classifiers-regular and weighted ones-using three different metrics. Results show an impressive accuracy rate of 97% for TLD GCs that are correctly classified to either of the classes.

MeSH terms

Algorithms*
Equipment Design
Humans
Neural Networks, Computer*
Occupational Exposure / analysis*
Radiation Exposure / analysis*
Radiation Monitoring / methods*
Support Vector Machine
Thermoluminescent Dosimetry / instrumentation*