PMID- 37336914
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20230620
LR  - 20230701
IS  - 2045-2322 (Electronic)
IS  - 2045-2322 (Linking)
VI  - 13
IP  - 1
DP  - 2023 Jun 19
TI  - A comparison of machine learning methods to classify radioactive elements using 
      prompt-gamma-ray neutron activation data.
PG  - 9948
LID - 10.1038/s41598-023-36832-8 [doi]
LID - 9948
AB  - 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.
CI  - (c) 2023. The Author(s).
FAU - Mathew, Jino
AU  - Mathew J
AD  - Faculty of Engineering, Environment and Computing, Coventry University, Priory 
      Street, Coventry, CV1 5FB, UK. jino.mathew@coventry.ac.uk.
FAU - Kshirsagar, Rohit
AU  - Kshirsagar R
AD  - Factory of the Future Advanced Manufacturing Park, University of Sheffield AMRC, 
      Wallis Way, Catcliffe, Rotherham, S60 5TZ, UK.
FAU - Abidin, Dzariff Z
AU  - Abidin DZ
AD  - Faculty of Engineering, Environment and Computing, Coventry University, Priory 
      Street, Coventry, CV1 5FB, UK.
FAU - Griffin, James
AU  - Griffin J
AD  - Faculty of Engineering, Environment and Computing, Coventry University, Priory 
      Street, Coventry, CV1 5FB, UK.
FAU - Kanarachos, Stratis
AU  - Kanarachos S
AD  - Faculty of Engineering, Environment and Computing, Coventry University, Priory 
      Street, Coventry, CV1 5FB, UK.
FAU - James, Jithin
AU  - James J
AD  - Nissan Technical Centre, Cranfield Technology Park, Moulsoe Road, Cranfield, 
      Wharley End, Bedford, MK43 0DB, UK.
FAU - Alamaniotis, Miltiadis
AU  - Alamaniotis M
AD  - Applied Artificial Intelligence Laboratory, Department of Electrical and Computer 
      Engineering, University of Texas at San Antonio, San Antonio, TX, USA.
FAU - Fitzpatrick, Michael E
AU  - Fitzpatrick ME
AD  - Faculty of Engineering, Environment and Computing, Coventry University, Priory 
      Street, Coventry, CV1 5FB, UK.
LA  - eng
PT  - Journal Article
DEP - 20230619
PL  - England
TA  - Sci Rep
JT  - Scientific reports
JID - 101563288
SB  - IM
PMC - PMC10279725
COIS- The authors declare no competing interests.
EDAT- 2023/06/20 01:09
MHDA- 2023/06/20 01:10
PMCR- 2023/06/19
CRDT- 2023/06/19 23:17
PHST- 2023/01/26 00:00 [received]
PHST- 2023/06/10 00:00 [accepted]
PHST- 2023/06/20 01:10 [medline]
PHST- 2023/06/20 01:09 [pubmed]
PHST- 2023/06/19 23:17 [entrez]
PHST- 2023/06/19 00:00 [pmc-release]
AID - 10.1038/s41598-023-36832-8 [pii]
AID - 36832 [pii]
AID - 10.1038/s41598-023-36832-8 [doi]
PST - epublish
SO  - Sci Rep. 2023 Jun 19;13(1):9948. doi: 10.1038/s41598-023-36832-8.