苹果可溶性固形物近红外光谱检测的偏最小二乘回归变量筛选研究

为了提高苹果可溶性固形物含量近红外光谱校正模型的预测能力和稳健性，分别采用反向区间偏最小二乘法、遗传算法和连续投影算法，筛选苹果可溶性固形物的近红外光谱变量，并建立了偏最小二乘回归模型。利用遗传算法筛选的141个变量建立的校正模型，预测效果最好，与全谱建立的校正模型比较，预测相关系数，从0.93提高到0.96，预测均方根误差，从0.30°Brix降低到0.23°Brix。实验结果表明遗传算法结合偏最小二乘回归方法，有效地提高了苹果可溶性固形物近红外光谱检测模型的预测精度。

Partial Least Squares Regression Variable Screening Studies on Apple Soluble Solids NIR Spectral Detection

To improve the predictive ability and robustness of the NIR correction model of the soluble solid content (SSC) of apple, the reverse interval partial least squares method, genetic algorithm and the continuous projection method were implemented to select variables of the NIR spectroscopy of the soluble solid content (SSC) of apple, and the partial least squares regression model was established. By genetic algorithm for screening of the 141 variables of the correction model, prediction has the best effect. And compared to the full spectrum correction model, the correlation coefficient increased to 0.96 from 0.93, forecast root mean square error decreased from 0.30°Brix to 0.23°Brix. This experimental results show that the genetic algorithm combined with partial least squares regression method improved the detection precision of the NIR model of the soluble solid content (SSC) of apple.