School of Information Engineering, Zhejiang A & F University, Hangzhou 311300, China.
College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China.
Sensors (Basel). 2018 Jun 1;18(6):1764. doi: 10.3390/s18061764.
Hyperspectral imaging was explored to detect stem rot (SSR) on oilseed rape leaves with chemometric methods, and the influences of variable selection, machine learning, and calibration transfer methods on detection performances were evaluated. Three different sample sets containing healthy and infected oilseed rape leaves were acquired under different imaging acquisition parameters. Four discriminant models were built using full spectra, including partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM), soft independent modeling of class analogies (SIMCA), and k-nearest neighbors (KNN). PLS-DA and SVM models were also built with the optimal wavelengths selected by principal component analysis (PCA) loadings, second derivative spectra, competitive adaptive reweighted sampling (CARS), and successive projections algorithm (SPA). The optimal wavelengths selected for each sample set by different methods were different; however, the optimal wavelengths selected by PCA loadings and second derivative spectra showed similarity between different sample sets. Direct standardization (DS) was successfully applied to reduce spectral differences among different sample sets. Overall, the results demonstrated that using hyperspectral imaging with chemometrics for plant disease detection can be efficient and will also help in the selection of optimal variable selection, machine learning, and calibration transfer methods for fast and accurate plant disease detection.
利用化学计量学方法探索了基于高光谱成像技术的油菜叶片茎基溃疡病（SSR）检测方法，并评估了变量选择、机器学习和校准传递方法对检测性能的影响。在不同的成像采集参数下，采集了包含健康和感染油菜叶片的三个不同样本集。使用全光谱构建了四个判别模型，包括偏最小二乘判别分析（PLS-DA）、支持向量机（SVM）、软独立建模分类类比（SIMCA）和 K 最近邻（KNN）。还使用主成分分析（PCA）载荷、二阶导数光谱、竞争自适应重加权采样（CARS）和连续投影算法（SPA）选择的最优波长构建了 PLS-DA 和 SVM 模型。不同方法为每个样本集选择的最优波长不同；然而，PCA 载荷和二阶导数光谱选择的最优波长在不同样本集之间表现出相似性。直接标准化（DS）成功地应用于减少不同样本集之间的光谱差异。总的来说，结果表明，使用高光谱成像技术和化学计量学进行植物病害检测是有效的，也有助于选择最优的变量选择、机器学习和校准传递方法，以实现快速准确的植物病害检测。
