Unsupervised Source Separation Technique for Multi-speciation Using a Single Laser: Quantifying Hydrocarbons without their Reference Spectra

Mohamed Sy, Emad Al Ibrahim, Ali Elkhazraji, Aamir Farooq

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present an autoencoder that can infer molar fractions and reference spectra based solely on mixture spectra. The model is demonstrated to work for C1-C3 hydrocarbon gas mixtures measured using an interband cascade laser. This method can ease the dependence of spectroscopic sensing on reference spectra.

Original languageEnglish
Title of host publication2024 Conference on Lasers and Electro-Optics, CLEO 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781957171395
StatePublished - 2024
Externally publishedYes
Event2024 Conference on Lasers and Electro-Optics, CLEO 2024 - Charlotte, United States
Duration: 7 May 202410 May 2024

Publication series

Name2024 Conference on Lasers and Electro-Optics, CLEO 2024

Conference

Conference2024 Conference on Lasers and Electro-Optics, CLEO 2024
Country/TerritoryUnited States
CityCharlotte
Period7/05/2410/05/24

Bibliographical note

Publisher Copyright:
CLEO 2024 © Optica Publishing Group 2024 © 2024 The Author(s)

Keywords

  • Hydrocarbons
  • Laser modes
  • Lasers and electrooptics
  • Measurement by laser beam
  • Quantum cascade lasers
  • Sensors
  • Temperature distribution
  • Temperature measurement
  • Temperature sensors
  • Training

ASJC Scopus subject areas

  • Process Chemistry and Technology
  • Computer Networks and Communications
  • Civil and Structural Engineering
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Instrumentation
  • Atomic and Molecular Physics, and Optics

Fingerprint

Dive into the research topics of 'Unsupervised Source Separation Technique for Multi-speciation Using a Single Laser: Quantifying Hydrocarbons without their Reference Spectra'. Together they form a unique fingerprint.

Cite this