Skip to Main Content
Skip Nav Destination
ASME Press Select Proceedings
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
Editor
C. H. Dagli
C. H. Dagli
Search for other works by this author on:
ISBN-10:
0791802655
No. of Pages:
650
Publisher:
ASME Press
Publication date:
2007

Water vapor absorption significantly distorts the spectra of compounds that are measured in atmospheric air and makes it difficult to identify the compounds' terahertz fingerprints. To get clean spectra, it's necessary to measure the compounds in nitrogen environment or to measure another reference spectrum in air. But both methods face problems in real-life application scenarios, in which compounds are measured in atmospheric air with unknown and varying humidity. In this paper, Independent Component Analysis (ICA) is used to separate the water vapor absorption features from the Terahertz spectra of compounds that are measured in atmospheric air. The cleaned Terahertz spectra using ICA are compared with the reference spectra measured in nitrogen, which do not contain water vapor absorption features. Results show that ICA can effectively remove water vapor features from the compounds with only a single measurement.

Abstract
Introduction
Terahertz Spectra Data
ICA Algorithms
ICA for Extracting the Water Vapor Spectrum
ICA for Removing Water Vapor Features from RDX and HMX
Conclusions
Acknowledgement
References
This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal