Adaptive Artificial Neural Network in near infrared spectroscopy for standard-free calibration transfer

Yap, Xien Yin; Chia, Kim Seng; Suarin, Nur Aisyah Syafinaz

doi:10.1016/j.chemolab.2022.104674

Cited by 8 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Factor analysis (FA) is a highly effective method for establishing relationships between two sets of measurements (spectrum of two instruments). Transfer methods based on factor analysis, such as the Spectral Space Transformation algorithm (SST) (L. Li et al 2022;Du et al 2011), the alternating trilinear decomposition (ATLD) algorithm (Yap et al 2022), the Principal Component Analysis (PCA) algorithm (Rehman et al 2022), and the Canonical Correlation Analysis (CCA) algorithm (Fan et al 2008;Zheng et al 2014), have been widely applied and are frequently compared to traditional methods. FA, in contrast to PCR or PLS (Mendoza et al 2018), utilizes correlation rather than covariance.…”

Section: Introductionmentioning

confidence: 99%

Non-destructive testing of mechanical properties of solid wood panel based on partial least squares structural equation modeling transfer method

Jiang

Zhang

Chen

2023

BioRes

View full text Add to dashboard Cite

Calibration transfer between near infrared (NIR) spectrometers is a subtle issue in the chemometrics and process industry. Similar instruments may generate strongly different spectral responses, and regression models developed on a first NIR system can rarely be used with spectra collected by a second apparatus. In this work, two novel methods based on Structural Equation Modeling (SEM), called Enhanced Feature Extraction Approaches for factor analysis (EFEA-FA) and Enhanced Feature Extraction Approaches for spectral space transformation (EFEA-SST), were proposed to perform calibration transfer between NIR spectrometers. They were applied to a NIR nondestructive testing model for solid wood panels mechanical properties. Four different standardization algorithms were evaluated for transferring solid wood panels quality databases between a portable NIRS (InGaAs)-array spectrometer (NIRquest512) and a HSI Camera (SPECIM FX17). The results showed that EFEA-SST yielded the best model evaluation metrics (R2 and Root Mean Square Error of Prediction (RMSEP)) values for tensile strength (RMSEP=11.309, R2=0.865) parameters, while EFEA-FA gave the best fit for flexural strength (RMSEP=10.653, R2=0. 912). These results suggest the potential of two novel quality parameters prediction methods based on spectral databases transferred between diverse NIRS spectrometers.

show abstract