Improving differentiation of two groups by combining scores fromindependent spectral ranges

Abstract

Principle Component Analysis (PCA) has been widely used in the field of vibrational spectroscopy for qualitative analysis by representing large spectral data by a few feature-containing variables or scores. Although multiple spectral ranges are often used for PCA, only one series of scores generated by merging selected spectral ranges is conventionally used for target analysis. The use of independent series of scores generated from separate spectral ranges has not been exploited. The aim of this study was to evaluate possible improvement in the differentiation of the two groups by utilizing scores independently generated from separate spectral ranges.