State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.
State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2018 May 5;196:131-140. doi: 10.1016/j.saa.2018.02.017. Epub 2018 Feb 6.
Corn starch is an important material which has been traditionally used in the fields of food and chemical industry. In order to enhance the rapidness and reliability of the determination for starch content in corn, a methodology is proposed in this work, using an optimal CC-PLSR-RBFNN calibration model and near-infrared (NIR) spectroscopy. The proposed model was developed based on the optimal selection of crucial parameters and the combination of correlation coefficient method (CC), partial least squares regression (PLSR) and radial basis function neural network (RBFNN). To test the performance of the model, a standard NIR spectroscopy data set was introduced, containing spectral information and chemical reference measurements of 80 corn samples. For comparison, several other models based on the identical data set were also briefly discussed. In this process, the root mean square error of prediction (RMSEP) and coefficient of determination (Rp) in the prediction set were used to make evaluations. As a result, the proposed model presented the best predictive performance with the smallest RMSEP (0.0497%) and the highest Rp (0.9968). Therefore, the proposed method combining NIR spectroscopy with the optimal CC-PLSR-RBFNN model can be helpful to determine starch content in corn.
玉米淀粉是一种重要的材料，在食品和化学工业领域有着传统的应用。为了提高玉米中淀粉含量测定的快速性和可靠性，本工作提出了一种使用近红外（NIR）光谱和最优 CC-PLSR-RBFNN 校准模型的方法。该模型基于关键参数的最优选择以及相关系数法（CC）、偏最小二乘回归（PLSR）和径向基函数神经网络（RBFNN）的组合来开发。为了测试模型的性能，引入了一个标准的 NIR 光谱数据集，其中包含 80 个玉米样品的光谱信息和化学参考测量值。为了进行比较，还简要讨论了基于相同数据集的其他几种模型。在此过程中，使用预测集中的均方根误差预测值（RMSEP）和决定系数（Rp）进行评估。结果表明，所提出的模型具有最佳的预测性能，RMSEP（0.0497%）最小，Rp（0.9968）最高。因此，结合 NIR 光谱和最优 CC-PLSR-RBFNN 模型的方法有助于确定玉米中的淀粉含量。
