Element-specific determination of X-ray transmission signatures using neural networks

C.R. Day, J.C. Austin, J.B. Butcher, P.W. Haycock, A.T. Kearon

Research output: Contribution to journalArticle

Abstract

In this article, we report on the application of neural networks to the problem of making an element-specific determination of unknown metal targets based on the characteristics of their transmitted X-ray signatures. Our method was applied to two groups of metal targets that we characterised as light elements (atomic numbers between 40 and 50) and heavy elements (atomic numbers between 73 and 83). In all cases their X-ray signatures were pre-processed; randomly allocated into training and testing datasets; and then presented to a self-organising map neural network in order to perform the element-specific determination. The technique was able to make a correct determination of unknown metal targets with an accuracy of 95% for the heavy elements and 99% for the light elements.
Original languageEnglish
Pages (from-to)446-451
JournalNDT & E International
Volume42
Issue number5
DOIs
Publication statusPublished - Jul 2009

Fingerprint

light elements
signatures
heavy elements
metals
x rays
organizing
education

Cite this

Day, C. R., Austin, J. C., Butcher, J. B., Haycock, P. W., & Kearon, A. T. (2009). Element-specific determination of X-ray transmission signatures using neural networks. NDT & E International, 42(5), 446-451. https://doi.org/10.1016/j.ndteint.2009.02.005
Day, C.R. ; Austin, J.C. ; Butcher, J.B. ; Haycock, P.W. ; Kearon, A.T. / Element-specific determination of X-ray transmission signatures using neural networks. In: NDT & E International. 2009 ; Vol. 42, No. 5. pp. 446-451.
@article{bab992c0f54549f9b497e7e502608a79,
title = "Element-specific determination of X-ray transmission signatures using neural networks",
abstract = "In this article, we report on the application of neural networks to the problem of making an element-specific determination of unknown metal targets based on the characteristics of their transmitted X-ray signatures. Our method was applied to two groups of metal targets that we characterised as light elements (atomic numbers between 40 and 50) and heavy elements (atomic numbers between 73 and 83). In all cases their X-ray signatures were pre-processed; randomly allocated into training and testing datasets; and then presented to a self-organising map neural network in order to perform the element-specific determination. The technique was able to make a correct determination of unknown metal targets with an accuracy of 95{\%} for the heavy elements and 99{\%} for the light elements.",
author = "C.R. Day and J.C. Austin and J.B. Butcher and P.W. Haycock and A.T. Kearon",
year = "2009",
month = "7",
doi = "10.1016/j.ndteint.2009.02.005",
language = "English",
volume = "42",
pages = "446--451",
number = "5",

}

Day, CR, Austin, JC, Butcher, JB, Haycock, PW & Kearon, AT 2009, 'Element-specific determination of X-ray transmission signatures using neural networks', NDT & E International, vol. 42, no. 5, pp. 446-451. https://doi.org/10.1016/j.ndteint.2009.02.005

Element-specific determination of X-ray transmission signatures using neural networks. / Day, C.R.; Austin, J.C.; Butcher, J.B.; Haycock, P.W.; Kearon, A.T.

In: NDT & E International, Vol. 42, No. 5, 07.2009, p. 446-451.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Element-specific determination of X-ray transmission signatures using neural networks

AU - Day, C.R.

AU - Austin, J.C.

AU - Butcher, J.B.

AU - Haycock, P.W.

AU - Kearon, A.T.

PY - 2009/7

Y1 - 2009/7

N2 - In this article, we report on the application of neural networks to the problem of making an element-specific determination of unknown metal targets based on the characteristics of their transmitted X-ray signatures. Our method was applied to two groups of metal targets that we characterised as light elements (atomic numbers between 40 and 50) and heavy elements (atomic numbers between 73 and 83). In all cases their X-ray signatures were pre-processed; randomly allocated into training and testing datasets; and then presented to a self-organising map neural network in order to perform the element-specific determination. The technique was able to make a correct determination of unknown metal targets with an accuracy of 95% for the heavy elements and 99% for the light elements.

AB - In this article, we report on the application of neural networks to the problem of making an element-specific determination of unknown metal targets based on the characteristics of their transmitted X-ray signatures. Our method was applied to two groups of metal targets that we characterised as light elements (atomic numbers between 40 and 50) and heavy elements (atomic numbers between 73 and 83). In all cases their X-ray signatures were pre-processed; randomly allocated into training and testing datasets; and then presented to a self-organising map neural network in order to perform the element-specific determination. The technique was able to make a correct determination of unknown metal targets with an accuracy of 95% for the heavy elements and 99% for the light elements.

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-67349285433&partnerID=MN8TOARS

UR - https://www.sciencedirect.com/science/article/pii/S0963869509000309?via%3Dihub

U2 - 10.1016/j.ndteint.2009.02.005

DO - 10.1016/j.ndteint.2009.02.005

M3 - Article

VL - 42

SP - 446

EP - 451

IS - 5

ER -