基于间隔偏最小二乘法的农产品近红外光谱谱区选择方法

Selection of the Efficient Wavelength Regions in Agricultural Product NIR Spectroscopy based on Interval Partial Least-Squares(iPLS)

怎样建立准确的农产品内在质量的近红外光谱预测模型,一直是国内外近红外光谱分析者的研究重点,而现有的农产品近红外光谱数据建立光谱预测模型时,都要面临选择合适的光谱谱区的问题。本研究提出一种间隔偏最小二乘法的农产品近红外光谱谱区选择方法,并将其应用于建立苹果糖度近红外光谱模型。结果表明,该方法可以减小建模运算时间,剔除噪声过大的谱区,使最终建立的农产品品质检测近红外光谱模型的预测能力和精度更高。

Calibration is nowadays one of the most important fields of chemometrics, and agricultural product spectral data are perhaps the most common type of data to which chemometrics techniques are applied. GraphicaUy-oriented local multi- variate calibration modeling procedures called interval partial least-squares （iPLS） was applied to select the efficient spectral regions that provided the lowest prediction error. The optimal combinations of 5 spectral intervals among 40 intervals that selected by iPLS yielded a good result, iPLS model could diminish runtime and select the optimal intervals.