elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Comparison of Classification Methods for Spectral Data of Laser-induced Fluorescence

Kraus, Marian and Fellner, Lea and Gebert, Florian and Grünewald, Karin and Pargmann, Carsten and Walter, Arne and Duschek, Frank (2018) Comparison of Classification Methods for Spectral Data of Laser-induced Fluorescence. In: Enhancing CBRNE safety & security: Proceedings of the SICC 2017 Conference - Science as the first countermeasure for CBRNE and Cyber threats (1), pp. 49-57. Springer International Publishing. First Scientific International Conference on CBRNe, 22.-24. Mai 2017, Rom, Italien. DOI: 10.1007/978-3-319-91791-7 ISBN 978-3-319-91791-7

[img] PDF (Revised Version)
1MB
[img] PDF
1MB

Official URL: https://www.springer.com/us/book/9783319917900

Abstract

Online detection of CBRNE is a research field of growing importance due to its relevance for public security and defense. The selectivity of machine learning has reached maturity in order to distinguish very similar laser-induced fluorescence (LIF) spectra of different samples - establishing the basis for an automatic classification. The work in this contribution applies the classification process of decision trees, support vector machines and artificial neural networks to LIF spectra. Two experimental setups with two excitation wavelengths each (280 and 355 nm; 266 and 355 nm) and different spectral resolutions of about 1 nm and 12 nm, respectively, have been performed. In the first setup the discrimination of seven bacteria species with an accuracy of over 90 % is demonstrated. The data of the second setup with lower spectral resolution are equally sufficient for a subsequent classification. The results are compared and represented in a low-dimensional subspace for the purpose of visualization.

Item URL in elib:https://elib.dlr.de/114112/
Document Type:Conference or Workshop Item (Poster)
Title:Comparison of Classification Methods for Spectral Data of Laser-induced Fluorescence
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Kraus, MarianMarian.Kraus (at) dlr.dehttps://orcid.org/0000-0002-5385-9420
Fellner, Lealea.fellner (at) dlr.dehttps://orcid.org/0000-0002-1359-0260
Gebert, Florianflorian.gebert (at) dlr.deUNSPECIFIED
Grünewald, Karinkarin.gruenewald (at) dlr.dehttps://orcid.org/0000-0003-0922-2307
Pargmann, Carstencarsten.pargmann (at) dlr.dehttps://orcid.org/0000-0003-3688-6360
Walter, Arnearne.walter (at) dlr.dehttps://orcid.org/0000-0002-4377-9152
Duschek, Frankfrank.duschek (at) dlr.dehttps://orcid.org/0000-0002-1809-0257
Date:October 2018
Journal or Publication Title:Enhancing CBRNE safety & security: Proceedings of the SICC 2017 Conference - Science as the first countermeasure for CBRNE and Cyber threats
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI :10.1007/978-3-319-91791-7
Page Range:pp. 49-57
Editors:
EditorsEmail
D'Arienzo, MarcoUNSPECIFIED
Malizia, AndreaUNSPECIFIED
Publisher:Springer International Publishing
Series Name:Enhancing CBRNE Safety & Security: Proceedings of the SICC 2017 Conference
ISBN:978-3-319-91791-7
Status:Published
Keywords:Standoff detection; Laser-induced fluorescence spectra; Classification models; Machine learning; Decision trees; Support vector machines; Artificial neural networks
Event Title:First Scientific International Conference on CBRNe
Event Location:Rom, Italien
Event Type:international Conference
Event Dates:22.-24. Mai 2017
Organizer:HESAR
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:fixed-wing aircraft
DLR - Research area:Aeronautics
DLR - Program:L AR - Aircraft Research
DLR - Research theme (Project):L - Laser Research and Technology
Location: Lampoldshausen
Institutes and Institutions:Institute of Technical Physics > Atmospheric Propagation and Effect
Deposited By: Kraus, Marian
Deposited On:28 Nov 2017 10:56
Last Modified:31 Jul 2019 20:11

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.