Table 9 Results of models using MFCC and CQT features from CTGAN data.

From: Improved railway track faults detection using Mel-frequency cepstral coefficient and constant-Q transform features

Model

Class

Precision

Recall

F1 Score

Model

Class

Precision

Recall

F1 Score

DT

0

0.81

0.80

0.81

LR

0

1.00

1.00

1.00

1

0.91

0.92

0.91

1

1.00

1.00

1.00

2

0.83

0.82

0.82

2

1.00

1.00

1.00

Micro avg.

0.85

0.85

0.85

Micro avg.

1.00

1.00

1.00

Weighted avg.

0.85

0.85

0.85

Weighted avg.

1.00

1.00

1.00

Accuracy

0.85

Accuracy

1.00

SVC

0

1.00

1.00

1.00

NB

0

1.00

1.00

1.00

1

1.00

1.00

1.00

1

1.00

1.00

1.00

2

1.00

1.00

1.00

2

1.00

1.00

1.00

Micro avg.

1.00

1.00

1.00

Micro avg.

1.00

1.00

1.00

Weighted avg.

1.00

1.00

1.00

Weighted avg.

1.00

1.00

1.00

Accuracy

1.00

Accuracy

1.00

KNN

0

0.66

1.00

0.80

RF

0

1.00

1.00

1.00

1

1.00

0.03

0.07

1

1.00

1.00

1.00

2

0.37

0.55

0.45

2

1.00

1.00

1.00

Micro avg.

0.68

0.53

0.44

Micro avg.

1.00

1.00

1.00

Weighted avg.

0.68

0.52

0.43

Weighted avg.

1.00

1.00

1.00

Accuracy

0.52

Accuracy

1.00

Hard Voting

0

1.00

1.00

1.00

Soft Voting

0

1.00

1.00

1.00

1

1.00

1.00

1.00

1

1.00

1.00

1.00

2

1.00

1.00

1.00

2

1.00

1.00

1.00

Micro avg.

1.00

1.00

1.00

Micro avg.

1.00

1.00

1.00

Weighted avg.

1.00

1.00

1.00

Weighted avg.

1.00

1.00

1.00

Accuracy

1.00

Accuracy

1.00