在波长450-2500 nm范围提取189个砂糖橘的漫反射光谱,使用sym8小波的3层分解对其进行去噪预处理,引入连续投影算法(SPA)对光谱进行压缩,从2051个波长中初步提取14个优选波长,以这14个波长建立的多元线性回归模型(MLR)的预测相关系数为0.8855,预测均方根误差为0.5111,效果优于全谱偏最小二乘模型(PLS).通过贡献值进一步筛选,提取11个特征波长,以这11个特征波长建立的MLR模型、PLS模型和BP神经网络模型(BPNN)都与14个优选波长建立的相应模型效果相当.结果表明,连续投影算法结合贡献值筛选可以将波长变量数缩减到全谱变量的0.54%,简化定量模型的结构,增强模型精度和稳健性;同时被选择的波长物理意义明确,模型解释能力增强.%The reflectance spectra of 189 samples within 450 ~ 2 500 nm were collected. Firstly, the spectra were denoised using the orthogonal wavelet functions sym8 (level was 3 ). And then the spectra variables were compressed to 14 variables by successive projections algorithm (SPA). The MLR model with 14 variables as inputs could result in that prediction correlation coefficient was 0. 885 5 and prediction root mean square error was 0. 511 1. Then the group of wavelengths derived from SPA was screened by their contributions to the total sugar content. After screening on contribution, the number of wavelength variables dropped to 11. Finally, the MLR, PLS and BPNN calibration models were built with 11 wavelength variables as inputs and compared. The results demonstrated that wavelength variables were decreased to 0. 54 % of the original variables by SPA and screening on contribution, and this could help to make the model more concise and robust.
展开▼
