TY - JOUR
T1 - Classification of Non-Referenced Continuous-Wave Terahertz Reflection Spectra for Remote Material Identification
AU - Kristensen, Mathias Hedegaard
AU - Cielecki, Pawel Piotr
AU - Skovsen, Esben
PY - 2024/8
Y1 - 2024/8
N2 - Commonly, terahertz spectra (both continuous-wave and pulsed) are deconvoluted by reference spectra to remove the water vapor absorption lines and other system related responses. However, in real-life applications obtaining reference spectra can be problematic and adds to the complexity of the system. Thus, a reference-free method for classification of terahertz spectra could be a welcomed advance for remote sensing applications. In this paper, we study how simple machine learning algorithms perform as a reference-free method for terahertz stand-off identification of materials. The algorithms are trained using spectra measured under controlled humidity conditions and tested by a completely independent data set measured under ambient conditions. We apply three different classification algorithms; namely a Gaussian Bayes model, the k nearest neighbors, and a support vector machine. We found that, if the terahertz spectra are processed using a supervised algorithm (Regularized Linear Discriminant Analysis), very high classification scores (¿98.6%) can be retained for the non-referenced spectra. Moreover, the high accuracy is obtained meanwhile the dimensionality is reduced by a factor larger than 160, which further reduces the computational requirements. Hence, we have demonstrated that simple supervised machine learning algorithms can serve as a highly accurate reference-free method for THz material identification. This could be of great importance for real-world remote sensing applications based on terahertz spectroscopy.
AB - Commonly, terahertz spectra (both continuous-wave and pulsed) are deconvoluted by reference spectra to remove the water vapor absorption lines and other system related responses. However, in real-life applications obtaining reference spectra can be problematic and adds to the complexity of the system. Thus, a reference-free method for classification of terahertz spectra could be a welcomed advance for remote sensing applications. In this paper, we study how simple machine learning algorithms perform as a reference-free method for terahertz stand-off identification of materials. The algorithms are trained using spectra measured under controlled humidity conditions and tested by a completely independent data set measured under ambient conditions. We apply three different classification algorithms; namely a Gaussian Bayes model, the k nearest neighbors, and a support vector machine. We found that, if the terahertz spectra are processed using a supervised algorithm (Regularized Linear Discriminant Analysis), very high classification scores (¿98.6%) can be retained for the non-referenced spectra. Moreover, the high accuracy is obtained meanwhile the dimensionality is reduced by a factor larger than 160, which further reduces the computational requirements. Hence, we have demonstrated that simple supervised machine learning algorithms can serve as a highly accurate reference-free method for THz material identification. This could be of great importance for real-world remote sensing applications based on terahertz spectroscopy.
KW - Classification algorithms
KW - Reflection spectroscopy
KW - Remote sensing
KW - Terahertz (THz)
KW - Continuous-wave terahertz
KW - Dimensionality reduction
KW - Linear discriminant analysis
KW - Machine learning
KW - Material identification
KW - Principal component analysis
KW - Terahertz frequency-domain spectroscopy
KW - Terahertz reflection spectroscopy
KW - Terahertz remote sensing
KW - Terahertz screening
UR - http://www.scopus.com/inward/record.url?scp=85197021383&partnerID=8YFLogxK
U2 - 10.1016/j.infrared.2024.105420
DO - 10.1016/j.infrared.2024.105420
M3 - Journal article
SN - 1350-4495
VL - 140
JO - Infrared Physics and Technology
JF - Infrared Physics and Technology
M1 - 105420
ER -