Improved detection of highly energetic materials traces on surfaces by standoff laser-induced thermal emission incorporating neural networks

Amanda Figueroa-Navedo; Nataly Y. Galán-Freyle; Leonardo C. Pacheco-Londoño; Samuel P. Hernández-Rivera

doi:10.1117/12.2030978

3 June 2013 Improved detection of highly energetic materials traces on surfaces by standoff laser-induced thermal emission incorporating neural networks

Amanda Figueroa-Navedo, Nataly Y. Galán-Freyle, Leonardo C. Pacheco-Londoño, Samuel P. Hernández-Rivera

Author Affiliations +

Proceedings Volume 8705, Thermosense: Thermal Infrared Applications XXXV; 87050D (2013) https://doi.org/10.1117/12.2030978
Event: SPIE Defense, Security, and Sensing, 2013, Baltimore, Maryland, United States

Abstract

Terrorists conceal highly energetic materials (HEM) as Improvised Explosive Devices (IED) in various types of materials such as PVC, wood, Teflon, aluminum, acrylic, carton and rubber to disguise them from detection equipment used by military and security agency personnel. Infrared emissions (IREs) of substrates, with and without HEM, were measured to generate models for detection and discrimination. Multivariable analysis techniques such as principal component analysis (PCA), soft independent modeling by class analogy (SIMCA), partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM) and neural networks (NN) were employed to generate models, in which the emission of IR light from heated samples was stimulated using a CO₂ laser giving rise to laser induced thermal emission (LITE) of HEMs. Traces of a specific target threat chemical explosive: PETN in surface concentrations of 10 to 300 ug/cm²were studied on the surfaces mentioned. Custom built experimental setup used a CO₂ laser as a heating source positioned with a telescope, where a minimal loss in reflective optics was reported, for the Mid-IR at a distance of 4 m and 32 scans at 10 s. SVM-DA resulted in the best statistical technique for a discrimination performance of 97%. PLS-DA accurately predicted over 94% and NN 88%.

Citation Download Citation

Amanda Figueroa-Navedo, Nataly Y. Galán-Freyle, Leonardo C. Pacheco-Londoño, and Samuel P. Hernández-Rivera "Improved detection of highly energetic materials traces on surfaces by standoff laser-induced thermal emission incorporating neural networks", Proc. SPIE 8705, Thermosense: Thermal Infrared Applications XXXV, 87050D (3 June 2013); https://doi.org/10.1117/12.2030978

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available