...PLS-GA)在校正模型中用来筛选特征光谱区域和波长,通过交互验证法确定模型的主成分因子数和筛选的波长,并以预测均方根误差(RMSEP)和相关系数(Ru)作为模型的评价标准.基于siPLS-GA的最优模型包含4个光谱区、96个变量和10个主成分因子.
基于556个网页-相关网页
The correlation coefficients (r) and root mean square error of prediction (RMSEP) were used as the model evaluation indices.
以预测集的预测相关系数(r)，预测标准偏差(RMSEP)作为模型评价指标。
The correlation and RMSEP of themodel using selected 11 wavelengths to reduce the calculation of modeling is 0.95and 0.68%, respectively.
为了减少建模计算工作量，利用蛋白质在近红外光谱区的11个特征吸收峰进行了波长优选，建模的相关系数为0.95，RMSEP为0.68%。
Result:The coefficients of correlation of inner cross validation and external validation are both above 0.90, and the RMSECV and RMSEP are both below 0.05.
结果：所建的5个模型对验证集样品水分含量的预测值与实测值的相关系数均在0.90以上，预测误差均方根（RMSEP）均在0.05以下。
应用推荐