Raman spectroscopy analysis based on fourier transform for ABO blood group identification

Abstract

ABO blood type research is not only used for transfusion medicine, but also for the study of some diseases. In this study, principal component analysis is used to take the ABO blood group Raman spectrum of the Fourier transform, in order to improve the ABO blood typing sample recognition rate. When the principal component analysis is performed directly on the Raman spectrum, the differences between the ABO three blood samples can not be well recognized by the score data of the second and the twentieth main components. The Raman spectra of the fluorescence background is extracted from the Raman spectra by Fourier transform, so the imaginary part of the Raman spectrum is obtained. Then, the principal component of the imaginary part signal is analyzed, and fractional graphs of the second principal component and the twentieth principal component are used. In this way, the blood samples of type A, type B and O type are distinguished. The experimental results show that the principal component analysis is carried out by Fourier transform to improve the clustering effect of spectral data, making ABO three blood groups easier to be distinguished. The reason for the enhancement of the clustering effect is that the internal difference of the same kind of spectral data will be reduced and that the difference of the spectral data of different classes will be increased by Fourier transform.