Application of the radial basis function neural networks to improve the nondestructive Vis/NIR spectrophotometric analysis of potassium in fresh lettuces
Application of the radial basis function neural networks to improve the nondestructive Vis/NIR spectrophotometric analysis of potassium in fresh lettuces
复制标题
DOI：
10.1016/j.jfoodeng.2020.110417
复制
发表时间：
2020-12
影响因子：
5.5
通讯作者：
Yating Xiong;S. Ohashi;K. Nakano;W. Jiang;K. Takizawa;Kazuyuki Iijima;Phonkrit Maniwara
中科院分区：
文献类型：
--
作者：
Yating Xiong;S. Ohashi;K. Nakano;W. Jiang;K. Takizawa;Kazuyuki Iijima;Phonkrit Maniwara
本研究旨在评估使用可见光/近红外（Vis/NIR）光谱法测定单一品种生菜和两个品种混合生菜叶子和叶柄中钾浓度的可行性。作为开发预测模型的回归工具，对偏最小二乘（PLS）和径向基函数（RBF）神经网络进行了系统的研究和比较。应用竞争性自适应重加权采样（CARS）变量选择和光谱预处理（一阶和二阶导数）来优化预测性能。基于这些选定的最佳波长，建立的 PLS 预测模型的绿叶和叶柄的决定系数 (R2) 分别为 0.83 和 0.71，残差预测偏差 (RPD) 分别为 1.95 和 1.80，预测均方根误差 (RMSEP) 分别为 39.07 和 38.06 mg/100 g。通过比较，发现采用一阶导数预处理光谱的 RBF 方法可提供混合样品的最佳性能，绿叶和叶柄的 R2 分别为 0.86 和 0.88，RMSEP 为 31.20 和 27.63 mg/100 g，RPD 为 2.44 和 2.47。这项研究的总体结果揭示了使用可见光/近红外光谱作为一种客观且非破坏性的方法来检查新鲜生菜的钾浓度的潜力。
This study was carried out to evaluate the feasibility of using Vis/near-infrared (Vis/NIR) spectroscopy for determining the potassium concentration in fresh lettuce leaves and petioles of single-variety lettuce and mixed lettuce leaves of two varieties. Partial least squares (PLS) and radial basis function (RBF) neural network were systemically studied and compared as regressions tools in developing the prediction models. Competitive adaptive reweighted sampling (CARS) variable selection and spectral preprocessing (first- and second-order derivatives) were applied to optimize the performance of predictions. On the basis of these selected optimum wavelengths, the established PLS prediction models provided the coefficients of determination (R2) of 0.83 and 0.71, residual predictive deviations (RPD) were 1.95 and 1.80, and root mean square errors of prediction (RMSEP) were 39.07 and 38.06 mg/100 g for green leaves and petioles, respectively. By comparison, the RBF approach with first-derivative preprocessing spectra was found to provide the best performance of mixed samples, yielding R2of 0.86 and 0.88, RMSEP of 31.20 and 27.63 mg/100 g, and RPD of 2.44 and 2.47 for green leaves and petioles, respectively. The overall results of this study revealed the potential for use of Vis/NIR spectroscopy as an objective and non-destructive method to inspect the potassium concentration of fresh lettuces.