Aplication of Caliberation Model using Discrete Wavelet Transformation – Partial Least Square for Giengerol Data

Abstract

The determination of concentration of gingerol compound is usually carried out through a long and expensive process using HPLC instrument. The alternative method to predict such concentration can be done using a multivariate calibration model. Since the numbers of samples (n) are less than the number of variables (p) and between the independent variables are correlated, the development of model using conventional regression is no longer valid. The combination of Discrete Wavelet Transformation (DWT) and Partial Least Square has been adopted in this research to predict concentration of gingerol and it showed a promising result.