Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Summary of existing literature.

More »

Table 1 Expand

Table 2.

Summary statistics.

More »

Table 2 Expand

Fig 1.

Pair plot of all attributes with respect to number of uniform barriers.

More »

Fig 1 Expand

Fig 2.

Pair plot of all attributes with respect to number of Gaussian barriers.

More »

Fig 2 Expand

Fig 3.

Correlation heatmap of all attributes.

More »

Fig 3 Expand

Fig 4.

(a) Histogram of Number of Gaussian Barriers and (b) Histogram of Number of Uniform Barriers.

More »

Fig 4 Expand

Table 3.

Algorithm for hyperparameter tuning with ACO.

More »

Table 3 Expand

Fig 5.

Ranking of features according to feature importance.

More »

Fig 5 Expand

Table 4.

Algorithm for feature importance analysis.

More »

Table 4 Expand

Table 5.

Algorithm for regularization techniques application.

More »

Table 5 Expand

Table 6.

Algorithm for feature sensitivity analysis.

More »

Table 6 Expand

Table 7.

Initial regression model results.

More »

Table 7 Expand

Fig 6.

(a) Best Solution for ACO–SVR1 Model and (b) Best Solution for ACO–SVR2 Model.

More »

Fig 6 Expand

Table 8.

Results for ACO–SVR1 and ACO–SVR2 Model.

More »

Table 8 Expand

Table 9.

Percentage Improvement in ACO–optimized models compared to initial models.

More »

Table 9 Expand

Table 10.

Algorithm of ACO–SVR hyperparameter optimization.

More »

Table 10 Expand

Fig 7.

Scatter plot of actual vs. predicted values for SVR1 model.

More »

Fig 7 Expand

Fig 8.

Scatter plot of residual vs actual values for SVR1 model.

More »

Fig 8 Expand

Fig 9.

Scatter plot of actual vs. predicted values for SVR2 model.

More »

Fig 9 Expand

Fig 10.

Scatter plot of residual vs actual values for SVR2 model.

More »

Fig 10 Expand

Fig 11.

(a) Best Distance Over Iterations using ACO–SVR1 Model and (b) Best Distance Over Iterations using ACO–SVR2 Model.

More »

Fig 11 Expand

Fig 12.

(a) Best Solution and All Nodes for ACO–SVR1 Model and (b) Best Solution and All Nodes for ACO–SVR2 Model.

More »

Fig 12 Expand

Fig 13.

Scatter plot of actual vs. predicted values for ACO–SVR1 model.

More »

Fig 13 Expand

Fig 14.

Scatter plot of residual vs actual values for ACO–SVR1 model.

More »

Fig 14 Expand

Fig 15.

Scatter plot of actual vs. predicted values for ACO–SVR2 model.

More »

Fig 15 Expand

Fig 16.

Scatter plot of residual vs actual values for ACO–SVR2 model.

More »

Fig 16 Expand

Fig 17.

Scatter plot to compare SVR–1 with ACO–SVR1 model.

More »

Fig 17 Expand

Fig 18.

Scatter plot to compare SVR with ACO–SVR1 model.

More »

Fig 18 Expand

Table 11.

Summary of the results of hyperparameter tuning using ACO–SVR1 and ACO–SVR2 models.

More »

Table 11 Expand

Fig 19.

(a) Scatter Plot of Actual vs Predicted Values of Number of Barriers for Model 1 and (b) for Model 2.

More »

Fig 19 Expand

Fig 20.

(a) Plot of Residuals for Number of Barriers for Model 1 and (b) for Model 2.

More »

Fig 20 Expand

Fig 21.

Bar plot comparing the effect of L1 and L2 regularization on various metrics for model 1.

More »

Fig 21 Expand

Fig 22.

Plot comparing the effect of L1 and L2 regularization on various metrics for model 2.

More »

Fig 22 Expand

Fig 23.

(a) Scatter Plot to Compare the Initial vs Final Predictions for Model 1 (b) and for Model 2.

More »

Fig 23 Expand

Fig 24.

Bar plot illustrating the percentage improvement in performance metrics of final models.

More »

Fig 24 Expand