Table 13 K-fold cross-validation results with MFCC, CQT features using machine learning models.

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

Features

DT

SVC

KNN

LR

NB

RF

Voting (Hard)

Voting (Soft)

MFCC

0.93(± 0.08)

0.99 (± 0.02)

0.85 (± 0.08)

0.96 (± 0.05)

0.99 (± 0.02)

0.98 (± 0.02)

-

-

CQT

0.92(± 0.05)

0.94 (± 0.04)

0.80 (± 0.10)

0.90 (± 0.05)

0.72 (± 0.15)

0.95 (± 0.07)

0.94 (± 0.04)

0.94 (± 0.04)

MFCC+CQT

0.91(± 0.07)

0.95 (± 0.05)

0.83 (± 0.07)

0.90 (± 0.04)

0.48 (± 0.09)

0.95 (± 0.04)

0.94 (± 0.04)

0.90 (± 0.05)

Back to article page