High-Accuracy Material Classification via Reference-Free Terahertz Spectroscopy: Revisiting Spectral Referencing and Feature Selection

TL;DR

This study demonstrates that feature selection algorithms enable accurate, reference-free material classification using sparse terahertz spectroscopy, reducing the need for broadband sources and reference measurements.

Contribution

The paper introduces a data-driven feature selection approach that improves material classification accuracy in THz spectroscopy without reference spectra.

Findings

High classification accuracy with few spectral features

Selected features correspond to material absorption bands

Reference-free classification is feasible with sparse spectra

Abstract

We investigate how feature selection algorithms can enable accurate, reference-free classification of materials using sparse-frequency terahertz (THz) reflection spectroscopy. Three classes of feature selection strategies are evaluated. Namely, the filter-based mRMR (minimum Redundancy Maximum Relevance), the embedded LASSO (Least Absolute Shrinkage and Selection Operator), and the wrapper-based SFS (Sequential Forward Selection) algorithms. Each strategy is assessed using the Linear Logistic Regression, Na\"ive Bayes, and Support Vector Machine classifiers. Our results show that high classification accuracy can be achieved using only a small subset of frequencies. Particularly, when non-referenced spectra are applied. Furthermore, we show that the SFS-selected features align with the materials' absorption bands, confirming that the discriminative power arises from genuine spectroscopic contrasts. These findings highlights that reducing spectral dimensionality through data-driven selection eliminates the need for broadband sources and reference measurements, enabling compact, application-specific THz sensors. This approach offers robust material identification in real-world scenarios such as security screening, non-destructive testing, and environmental monitoring.