Skip to main content

Table 9 Classification results on the proposed feature selection approach for apple rust

From: A probabilistic segmentation and entropy-rank correlation-based feature selection approach for the recognition of fruit diseases

Method FPR Precision (%) Sensitivity (%) Specificity (%) FNR (%) Accuracy
DT 0.157 84.90 84.30 89.1 14.9 85.1
Q-SVM 0.096 90.05 90.30 90.9 9.6 93.6
C-SVM 0.070 92.15 92.90 90.9 7.4 92.6
QDA 0.157 83.95 84.15 70.9 18.1 81.9
F-KNN 0.061 93.2 93.8 92.7 6.4 93.6
W-KNN 0.103 88.50 89.60 81.8 11.7 88.3
EBT 0.096 90.05 90.30 90.9 9.6 92.6
ESDA 0.087 91.2 91.2 92.2 8.5 92.6
M-SVM 0.048 94.30 95.50 92.5 5.3 94.7
  1. The bold values indicate best results