期刊论文

Screening of NIR Spectral Variables of Starch in Tobacco and Establishment of Calibration Model

Liu, Jianli

中文

烟草科技

Tobacco Science and Technology

1002-0861

2015

48

8

37-43

10.16135/j.issn1002-0861.20150808

中国烟草总公司重庆市公司科技项目“重庆烟叶质量跟踪评价及风格特色区划研究”(NY20120802070020)。

本校为第一机构

为提高校正模型的预测精度,以烟草中淀粉近红外光谱(NIR)校正模型为研究对象,分别利用全光谱波段(FS)、方差光谱(VS)筛选光谱变量和遗传算法(GA)筛选光谱波长,结合偏最小二乘法建立校正模型(FS+PLS、VS+PLS和GA+PLS),并对100个初烤烟叶样品进行了预测。结果显示: ①FS+PLS(变量数1 557个)、VS+PLS(变量数781个)和GA+PLS(变量数72个)3种校正模型的决定系数R_c~2、交互验证均方根误差(RMSECV)分别为0.976 4、0.433,0.987 1、0.332和0.988 5、0.314。 ② 与FS+PLS和VS+PLS模型相比,GA+PLS模型的光谱变量数分别减少为FS和VS变量数的4.62%和9.22%,主因子数由15降至12,R_c~2明显提高,RMSECV显著降低。...

In order to improve the prediction precision of calibration model, the near infrared spectroscopy (NIR) calibration model for the starch in tobacco was studied. Spectral variables were chosen by means of full spectrum (FS) and variance spectrum (VS), spectral wavelength by means of genetic algorithm (GA), via partial least squares, the calibration models, FS+PLS, VS+PLS and GA+PLS, were established, and the starch contents in 100 flue-cured tobacco samples were predicted. The results showed that: 1) R<inf>c</inf><sup>2</sup>and root mean squares error of cross validatio...