Skip to main content

Table 3 Results for machine learning algorithm model accuracies developed using a sub-set of iron deficiency chlorosis data on a diverse set of soybean accessions

From: A real-time phenotyping framework using machine learning for plant stress severity rating in soybean

Algorithm Accuracy MPCAa Cross validated MPCA Interpretability Cost metric
CT 100.0 100.0 96.0 Medium 0.0000
KNN 99.7 96.7 95.0 Low 0.0031
RF 99.7 96.0 85.0 Low 0.0031
Hierarchyb 99.4 95.9 79.8 High 0.0062
QDA 99.4 92.0 98.9 Medium 0.0620
Hierarchyc 98.5 86.6 70.8 High 0.0155
GMMB 99.1 82.0 87.0 Medium 0.0093
NB 99.1 82.0 93.8 Medium 0.0093
LDA 98.8 79.3 84.3 High 0.0124
SVM 93.8 39.8 50.0 Low 0.1084
  1. aMean per class accuracy
  2. bSVM and SVM
  3. cLDA and SVM