连续小波变换-独立成分回归算法及其在多组分分析中的应用

ALGORITHM OF CONTINUOUS WAVELET TRANSFORM-INDEPENDENT COMPONENT REGRESSION AND ITS APPLICATION TO MULTICOMPONENT ANALYSIS

采用连续小波变换(CWT)对光谱数据进行处理,用独立成分分析(ICA)进行特征提取,再用回归分析方法对被测组分进行测定,建立了连续小波变换-独立成分回归(CWT-ICR)方法。方法用于肉样品中水分、脂肪和蛋白质多组分的同时测定,所得结果与化学法测得结果相符。

A new method of model construction based on continuous wavelet transform （CWT） and independent component regression （ICR） was proposed. In its application to near infrared spectrometry, the data of IR spectra were treated with CWT to remove the noise and spectral background, their characteristic matrix were then extracted by the independent component analysis, and finally, determination of the individual components of the sample was performed by the regression analysis. This new chemometric method has been applied to the simultaneous determination of contents of moisture, fat and protein in meat samples, showing that the results predicted by CWT-ICR method were in consistency with the results obtained by chemical analysis.