Improving reliability for classification of metallic objects using a WTMD portal

J. Makkonen; L. A. Marsh; J. Vihonen; A. Järvi; D. W. Armitage; A. Visa; A. J. Peyton

doi:10.1088/0957-0233/26/10/105103

Improving reliability for classification of metallic objects using a WTMD portal

J. Makkonen, L. A. Marsh, J. Vihonen, A. Järvi, D. W. Armitage, A. Visa, A. J. Peyton

Research output: Contribution to journal › Article › Scientific › peer-review

14 Citations (Scopus)

Abstract

In this paper, a walk-through metal detection (WTMD) portal is used for classification of metallic objects. The classification is based on the inversion of the magnetic polarisability tensor (tensor) of the object. The nature of bias and noise components in the tensor are examined by using real walk-through data, and consequently, a novel classifier is introduced. Furthermore, a novel method for detecting poorly inverted tensors is presented, enabling self-diagnostics for the WTMD portal. Based on the results, the novel methods increase the accuracy of metal object classification and have the potential to improve the reliability of a WTMD system.

Original language	English
Article number	105103
Journal	Measurement Science and Technology
Volume	26
Issue number	10
DOIs	https://doi.org/10.1088/0957-0233/26/10/105103
Publication status	Published - 26 Aug 2015
Publication type	A1 Journal article-refereed

Keywords

bias
classification
eigenvalues
electromagnetic polarisability
noise
tensor
WTMD

Publication forum classification

Publication forum level 2

ASJC Scopus subject areas

Applied Mathematics
Instrumentation

Access to Document

10.1088/0957-0233/26/10/105103

Cite this

@article{ee792ff6389842419aac21e935c23b71,

title = "Improving reliability for classification of metallic objects using a WTMD portal",

abstract = "In this paper, a walk-through metal detection (WTMD) portal is used for classification of metallic objects. The classification is based on the inversion of the magnetic polarisability tensor (tensor) of the object. The nature of bias and noise components in the tensor are examined by using real walk-through data, and consequently, a novel classifier is introduced. Furthermore, a novel method for detecting poorly inverted tensors is presented, enabling self-diagnostics for the WTMD portal. Based on the results, the novel methods increase the accuracy of metal object classification and have the potential to improve the reliability of a WTMD system.",

keywords = "bias, classification, eigenvalues, electromagnetic polarisability, noise, tensor, WTMD",

author = "J. Makkonen and Marsh, {L. A.} and J. Vihonen and A. J{\"a}rvi and Armitage, {D. W.} and A. Visa and Peyton, {A. J.}",

year = "2015",

month = aug,

day = "26",

doi = "10.1088/0957-0233/26/10/105103",

language = "English",

volume = "26",

journal = "Measurement Science and Technology",

issn = "0957-0233",

publisher = "IOP Publishing Ltd.",

number = "10",

}

TY - JOUR

T1 - Improving reliability for classification of metallic objects using a WTMD portal

AU - Makkonen, J.

AU - Marsh, L. A.

AU - Vihonen, J.

AU - Järvi, A.

AU - Armitage, D. W.

AU - Visa, A.

AU - Peyton, A. J.

PY - 2015/8/26

Y1 - 2015/8/26

N2 - In this paper, a walk-through metal detection (WTMD) portal is used for classification of metallic objects. The classification is based on the inversion of the magnetic polarisability tensor (tensor) of the object. The nature of bias and noise components in the tensor are examined by using real walk-through data, and consequently, a novel classifier is introduced. Furthermore, a novel method for detecting poorly inverted tensors is presented, enabling self-diagnostics for the WTMD portal. Based on the results, the novel methods increase the accuracy of metal object classification and have the potential to improve the reliability of a WTMD system.

AB - In this paper, a walk-through metal detection (WTMD) portal is used for classification of metallic objects. The classification is based on the inversion of the magnetic polarisability tensor (tensor) of the object. The nature of bias and noise components in the tensor are examined by using real walk-through data, and consequently, a novel classifier is introduced. Furthermore, a novel method for detecting poorly inverted tensors is presented, enabling self-diagnostics for the WTMD portal. Based on the results, the novel methods increase the accuracy of metal object classification and have the potential to improve the reliability of a WTMD system.

KW - bias

KW - classification

KW - eigenvalues

KW - electromagnetic polarisability

KW - noise

KW - tensor

KW - WTMD

U2 - 10.1088/0957-0233/26/10/105103

DO - 10.1088/0957-0233/26/10/105103

M3 - Article

AN - SCOPUS:84941975778

SN - 0957-0233

VL - 26

JO - Measurement Science and Technology

JF - Measurement Science and Technology

IS - 10

M1 - 105103

ER -

Improving reliability for classification of metallic objects using a WTMD portal

Abstract

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this