PCA model
Unsupervised PCA model
Parameters
Number of components
The number of component you want to detect and visualize.
Pretreatments
In top-down applied order ⬇️ , meaning Savitzky-Golay is applied first then Derivative and so on.
Savitzky-Golay
Derivative
SNV (Standard Normal Variate)
Logarithm
Center
UV (Unit Variance) scaling
For more on each type of pretreatment see: Pretreatments
Smooth
Smooth prediction result using median filter kernel
None
No Smoothing prediction.
Low
Smoothing using median filter kernel with 5x5 pixel box
Medium
Smoothing using median filter kernel with 10x10 pixel box
High
Smoothing using median filter kernel with 15x15 pixel box