Table 5 Analysis of confusion matrix for different diagnostic models.
From: Fault diagnosis using ISMA to optimize SVM parameters for aircraft engine damage repair
Different fault diagnosis models | / | Actual positive example | The actual counterexample | Accuracy (ACC) | Recall | F1 scores | P-value of t-test with ISMA-SVM |
|---|---|---|---|---|---|---|---|
PSO-SVM | Predict positive examples | TP = 800 | FP = 200 | 0.80 ± 0.04 | 0.84 ± 0.03 | 0.82 ± 0.03 | 0.002 |
Predict counterexamples | FN = 150 | TN = 1850 | |||||
WOA-SVM | Predict positive examples | TP = 750 | FP = 250 | 0.75 ± 0.05 | 079 ± 0.04 | 0.77 ± 0.04 | 0.001 |
Predict counterexamples | FN = 200 | TN = 18D0 | |||||
SMA-SVM | Predict positive examples | TP = 850 | FP = 150 | 0.85 ± 0.03 | 0.89 ± 0.02 | 0.87 ± 0.02 | 0.015 |
Predict counterexamples | FN = 100 | TN = 1900 | |||||
ISMA-SVM | Predict positive examples | TP = 900 | FP = 100 | 0.90 ± 0.02 | 0.95 ± 0.01 | 0.92 ± 0.01 | / |
Predict counterexamples | FN = 50 | TN = 1950 |
