Table 7 Avg and Std results of bKSHHO-KELM versus other models for predicting microseismic and blasting phenomena performance metrics.

From: A prediction model for microseismic signals based on kernel extreme learning machine optimized by Harris Hawks algorithm

Methods

Accuracy

Recall

Avg

Std

Avg

Std

bKSHHO-KELM

95.625%

0.019

93.964%

0.052

LightGBM

94.197%

0.013

90.033%

0.025

XGBoost

94.197%

0.018

90.061%

0.035

CatBoost

93.863%

0.021

90.256%

0.044

AdaBoost

91.840%

0.020

87.575%

0.046

RandomF

92.176%

0.021

87.578%

0.032

FKNN

90.326%

0.033

85.267%

0.071

KELM

92.093%

0.019

88.305%

0.049

Methods

Precision

F1 score

Avg

Std

Avg

Std

bKSHHO-KELM

92.632%

0.043

0.931

0.028

LightGBM

92.105%

0.033

0.910

0.021

XGBoost

92.105%

0.037

0.910

0.028

CatBoost

90.789%

0.048

0.904

0.033

AdaBoost

87.105%

0.049

0.872

0.032

RandomF

88.158%

0.064

0.877

0.036

FKNN

85.000%

0.057

0.849

0.049

KELM

87.105%

0.042

0.876

0.029

  1. Boldface indicates the best result in each column (ties are bolded).
Back to article page