A Wavelength Selection Method Based on Simple-to-Use Interactive Self-modeling Mixture Analysis for Near Infrared Spectroscopy

作者：Li Li Na; Li Qing Bo; Zhang Guang Jun^*

来源：Chinese Journal of Analytical Chemistry, 2009, 37(6): 823-827.

• Simple-to-use interactive self-modeling mixture analysis
• variable selection
• partial least squares
• near infrared spectroscopy
• quantitative calibration

In order to improve prediction accuracy and modeling efficiency for quantitative calibration in near infrared spectroscopy, a novel wavelength variable selection method based on SIMPLISMA (simple-to-use interactive self-modeling mixture analysis) was proposed. According to the value of purity and standard deviation, the wavelength with maximum information was selected. And then the correlation weight function was introduced to solve the colinearity between variables. By constructing quantitative calibration model with iteratively selected wavelength variables, the root mean square error of cross validation (RMSECV) was utilized to determinate the optimal number of selected variables. Two experimental NIR spectral data, four components mixture solution and plasma, for glucose concentration analysis were utilized to evaluate the proposed variable selection method. Only 0.3% variables of all spectra data for these two experimental data were used to quantitative calibration, and the root mean square error of prediction (RMSEP) of validation set of glucose concentration was decreased to 66.9 mg/dL and 1.5 mg/dL respectively. Comparing with the quantitative calibration model constructed with full spectral region and informative spectral band, the proposed variable selection method can minimize redundant information and is helpful to yield a more efficient calibration with higher prediction accuracy.

• 出版日期2009-6
• 单位北京航空航天大学