Plant Phenomics / 2020 / Article / Tab 1

Research Article

Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations

Table 1

Cross validation accuracy for each supervised classification algorithm evaluated.

MethodsBackgroundLeafStalkPanicleAverage

LDA1.0000.9690.9460.9740.972
PLS-DA1.0000.9730.9110.9760.965
ANN0.9970.9740.9230.9580.963
MLR0.9830.9700.9340.9590.962
SVM0.9990.9780.9200.9480.961
RF0.9990.9640.8300.9310.931
LASSO1.0000.9620.7540.9560.918
QDA0.9870.9860.6570.8650.874

LDA: linear discriminant analysis; MLR: multinomial logistic regression; ANN: artificial neural network; SVM: support vector machine; PLS-DA: partial least squares discriminant analysis; RF: random forest; QDA: quadratic discriminant analysis; LASSO: least absolute shrinkage and selection operator.