Plant Protection Department, Agricultural Institute of Slovenia, 1000 Ljubljana, Slovenia.
Sensors (Basel). 2022 Jan 4;22(1):367. doi: 10.3390/s22010367.
Hyperspectral imaging is a popular tool used for non-invasive plant disease detection. Data acquired with it usually consist of many correlated features; hence most of the acquired information is redundant. Dimensionality reduction methods are used to transform the data sets from high-dimensional, to low-dimensional (in this study to one or a few features). We have chosen six dimensionality reduction methods (partial least squares, linear discriminant analysis, principal component analysis, RandomForest, ReliefF, and Extreme gradient boosting) and tested their efficacy on a hyperspectral data set of potato tubers. The extracted or selected features were pipelined to support vector machine classifier and evaluated. Tubers were divided into two groups, healthy and infested with . The results show that all dimensionality reduction methods enabled successful identification of inoculated tubers. The best and most consistent results were obtained using linear discriminant analysis, with 100% accuracy in both potato tuber inside and outside images. Classification success was generally higher in the outside data set, than in the inside. Nevertheless, accuracy was in all cases above 0.6.
高光谱成像是一种用于非侵入式植物病害检测的常用工具。它获取的数据通常包含许多相关特征；因此，大部分获取的信息都是冗余的。降维方法用于将数据集从高维转换为低维（在本研究中转换为一个或几个特征）。我们选择了六种降维方法（偏最小二乘法、线性判别分析、主成分分析、随机森林、ReliefF 和极端梯度提升），并在马铃薯块茎的高光谱数据集上测试了它们的效果。提取或选择的特征被管道输送到支持向量机分类器进行评估。块茎被分为两组，健康和感染。结果表明，所有降维方法都能够成功识别接种的块茎。线性判别分析的效果最好且最一致，在马铃薯块茎内部和外部图像中均达到 100%的准确率。外部数据集的分类成功率普遍高于内部数据集。然而，在所有情况下，准确率都高于 0.6。
