Skip to main content

Table 2 Performances of PLSR regression models based on full bands

From: Quantitative visualization of lignocellulose components in transverse sections of moso bamboo based on FTIR macro- and micro-spectroscopy coupled with chemometrics

Constituent

LVs

R 2C

RMSEC

R 2P

RMSEP

RPD

Hemicellulose

16

0.850

0.010

0.780

0.012

2.131

Cellulose

17

0.918

0.008

0.836

0.012

2.466

Lignin

17

0.906

0.006

0.802

0.008

2.248

  1. LVs means the number of latent variables, R 2C and R 2P indicate the determination coefficients for the calibration and prediction, respectively, RMSEC and RMSEP represent the root mean square errors for the calibration and prediction, respectively, and RPD denotes the ratio of performance to deviation (similarly hereinafter)