梨枣糖度无损检测建模分析--基于高光谱成像技术

摘要

In Huping jujube for the study.Using the denoising and to base after full spectrum data and extract the 42 approximate coefficient model corresponding PLS and PCR respectively .Results show that:PLS model is built by using approximate coefficient correction set decision coefficient of Rc ( 0 .931 ) and PCR models Rc ( 0 .882 ) , respectively , than with a full spectrum PLS model is built by Rc (0.875) and PCR models Rc (0.858);PLS model calibration set variance RMSEC (0.986)、prediction set variance RMSEP (1.159) and PCR model calibration set variance RM-SEC (1.048)、prediction set variance RMSEP (1.322) compared with the full spectrum PLS model calibration set va-riance RMSEC (0.731)、prediction set variance RMSEP (1.270)and PCR model calibration set variance RMSEC (0.958)、prediction set variance RMSEP (1.361) difference value more close to.Explain application of approximate co-efficient of the model is stable .%以梨枣为对象，利用去噪和去基后的全光谱数据及提取的42个近似系数，分别建立相应的 PLS 和PCR 模型。结果分析表明：用近似系数所建的 PLS模型校正集决定系数 Rc（0．931）和 PCR 模型 Rc（0．882）分别比用全光谱所建的PLS模型Rc（0．875）和PCR模型Rc（0．858）要高；PLS 模型校正集方差RMSEC（0．986）、预测集方差RMSEP（1．159）和PCR 模型校正集方差RMSEC（1．048）、预测集方差 RMSEP（1．322）分别要比全光谱 PLS 模型校正集方差 RMSEC （0．731）、预测集方差 RMSEP （1．270）和 PCR 模型校正集方差 RMSEC （0．958）、预测集方差RMSEP（1．361）的差值更为接近。这说明，应用近似系数所建模型较稳定。