Table 4 Performance comparison of different machine learning models with 95% confidence intervals.

From: Comparison of deep learning models for predictive maintenance in industrial manufacturing systems using sensor data

Model

Accuracy (%)

Precision (%)

Recall (%)

F1-score (%)

SVM

89.3 ± 1.2

88.7 ± 1.4

87.2 ± 1.6

87.9 ± 1.3

Random forest

91.8 ± 0.9

91.2 ± 1.1

89.8 ± 1.3

90.5 ± 1.0

Logistic regression

87.6 ± 1.4

86.9 ± 1.6

85.4 ± 1.8

86.1 ± 1.5

CNN

95.2 ± 0.6

94.8 ± 0.8

93.6 ± 1.0

94.2 ± 0.6

LSTM

94.5 ± 0.8

93.9 ± 1.0

92.7 ± 1.2

93.3 ± 0.8

CNN-LSTM

96.1 ± 0.4

95.7 ± 0.6

94.8 ± 0.8

95.2 ± 0.4

Bidirectional LSTM

95.8 ± 0.6

95.3 ± 0.8

94.2 ± 1.0

94.7 ± 0.6

Attention-based LSTM

95.6 ± 0.6

95.1 ± 0.8

93.9 ± 1.0

94.5 ± 0.6

  1. Note: Results are reported with 95% confidence intervals, calculated from five independent runs. SVM = Support Vector Machine.
Back to article page