Application of independent component analysis (ICA) method to the Raman spectra processing

Abstract

Independent component analysis (ICA) method was applied as a processing step for Raman spectra. 136 Raman spectra were acquired from urine samples from 18 subjects. Each spectrum was acquired from different sample. 785nm, 100mW (at sample) laser with 2048 element linear silicon TE cooled CCD were used. In order to separate information of glucose, creatinine, urea nitrogen, uric acid and invaluable information from the urine spectrum, ICA by Maximum Likelihood (ML) fast fixed-point estimation algorithm was applied. By looking for maximum likelihood, independent information could be separated from the urine spectra. Among separated information, high frequency noise which could be generated by ambient noise and low frequency noise which contain information of baseline shift were observed. Additionally, peak information of each component was observed. The processing time was very short because fast fixed point algorithm was added to ML estimation method. Before applying ICA, all spectra were mean centered in order to enhance the peak information. In addition, all spectra were pre-processed to have unit variance in order to shorten calculation time. This first study about applying ICA suggested that this algorithm can be used as a pattern recognition algorithm to extract information from Raman spectra. Additionally, because ICA can provide information with statistical independency sufficiently, further studies about ICA which can substitute PCA will be performed.