2014
DOI: 10.2528/pierb14050704
|View full text |Cite
|
Sign up to set email alerts
|

Threat Target Classification Using Ann and SVM Based on a New Sensor Array System

Abstract: Electromagnetic imaging is based upon the fundamentals of electromagnetic (EM) fields and their relationship with the material properties under evaluation. A new system based on a Giant Magneto-Resistive (GMR) sensor array was built to capture the scattered EM signal returned by metallic objects. This paper evaluates the new system's capabilities through the classification of metallic objects based on features extracted from their response to EM fields. A novel amplitude variation feature as well as the combin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
1

Year Published

2015
2015
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 22 publications
0
3
1
Order By: Relevance
“…There is some also other previous research on the subject of metallic object classification using a WTMD portal. An approach based on EM imaging technology has been proposed by Al-Qubaa et al [15]. However, the used test set is limited, and although the results are not directly comparable, the reported classification accuracies seem lower than in our studies [4,5].…”
Section: Related Workcontrasting
confidence: 76%
“…There is some also other previous research on the subject of metallic object classification using a WTMD portal. An approach based on EM imaging technology has been proposed by Al-Qubaa et al [15]. However, the used test set is limited, and although the results are not directly comparable, the reported classification accuracies seem lower than in our studies [4,5].…”
Section: Related Workcontrasting
confidence: 76%
“…Then, the correct identification becomes unlikely. Al-Qubba et al [8] built a giant magneto-resistive sensor. They used an artificial neural network and support vector machines to recognise threat objects.…”
Section: Research On Wtmd and Bs Devicesmentioning
confidence: 99%
“…SVM raises the data dimension and linearizes the data; meanwhile there is almost no increase in computational complexity. Therefore, SVM is especially suitable for small samples and some inherently nonlinear problems [19,20] . This should be attributed to the kernel function and its expansion theory.…”
Section: Samples and Experimental Setupmentioning
confidence: 99%
“…ANN has good nonlinear mapping ability, and has priority in solving nonlinear problems of systems with components interaction. Nowadays, neural networks with different structures have been applied to spectral analysis [20,21] . In this paper, the Radical Basis Function (RBF) network was used, which is a three-layer feed-forward networks.…”
Section: Samples and Experimental Setupmentioning
confidence: 99%