Calibration transfer based on maximum margin criterion for qualitative analysis using Fourier transform infrared spectroscopy

Abstract

A traditional multivariate calibration transfer method such as piecewise direct standardization (PDS) is usually applied to quantitative analysis. To make the method apply to qualitative analysis of Fourier Transform Infrared spectroscopy (FTIR), we propose an improved calibration transfer method based on the maximum margin criterion (CTMMC). The new method not only considers the spectral changes under different conditions, but also takes into account the geometric characteristics of spectra from different classes, so the transformed spectra from different classes will be separated as far as possible, and this will improve the performance of the follow-up qualitative analysis. A comparative study is provided between the proposed method CTMMC and other traditional calibration transfer methods on two data sets. Experimental results show that the proposed method can achieve better performance than previous methods.