An ADAM Optimization for Water-Vapor Effect Removal in THz-TDS Data

Thanapirom, Chayut; Yi, Chia; Cota, Napat; Jintamethasawat, Rungroj; Kusolthossakul, Woraprach; Prasertsuk, Kiattiwut

doi:10.1109/irmmw-thz46771.2020.9370415

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The THz spectra of pure compounds have been explored using experimental and computational methods and reported in the literature. The absorption peaks observed in Figure , especially those in the 2.0–3.0 THz range, are in good agreement with previous THz-TDS studies on caffeine, quinic acid, and nicotinic acid …”

Section: Resultssupporting

confidence: 91%

Chemometric Analysis of a Ternary Mixture of Caffeine, Quinic Acid, and Nicotinic Acid by Terahertz Spectroscopy

et al. 2022

Self Cite

View full text Add to dashboard Cite

Caffeine, quinic acid, and nicotinic acid are among the significant chemical determinants of coffee quality. This study develops a chemometric model to quantify these compounds in ternary mixtures analyzed by terahertz time-domain spectroscopy (THz-TDS). A data set of 480 THz spectra was obtained from 80 samples. Combinations of data preprocessing methods, including normalization (Z-score, min-max scaling, Mie baseline removal) and dimensionality reduction (principal component analysis (PCA), factor analysis (FA), independent component analysis (ICA), locally linear embedding (LLE), non-negative matrix factorization (NMF), isomap), and prediction models (partial least-squares regression (PLSR), support vector regression (SVR), multilayer perceptron (MLP), convolutional neural network (CNN), gradient boosting) were analyzed for their prediction performance (totaling to 4,711,685 combinations). Results show that the highest quantification performance was achieved at a root-mean-square error of prediction (RMSEP) of 0.0254 (dimensionless mass ratio), using min-max scaling and factor analysis for data preprocessing and multilayer perceptron for prediction. Effects of preprocessing, comparison of prediction models, and linearity of data are discussed.

show abstract

Section: Resultssupporting

confidence: 91%