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.

NRCan dataset-based related work for fuel consumption and CO2 estimation.

More »

Table 1 Expand

Fig 1.

Methodology (A) Overall framework, (B) flowchart.

More »

Fig 1 Expand

Table 2.

Descriptive statistics of the combined datasets.

More »

Table 2 Expand

Fig 2.

Average fuel consumption per vehicle brand.

More »

Fig 2 Expand

Fig 3.

Average CO2 emission per vehicle brand.

More »

Fig 3 Expand

Fig 4.

Heatmap of quantitative independent variables.

More »

Fig 4 Expand

Table 3.

Tuned hyperparameters for consumption and emission models.

More »

Table 3 Expand

Table 4.

Energy consumption prediction results.

More »

Table 4 Expand

Fig 5.

Fuel consumption performance metrics of all ML models.

More »

Fig 5 Expand

Fig 6.

Actual versus predicted consumption plots: (A) Linear regression, (B) Ridge, (C) Lasso, (D) Elastic Net, (E) SVM, (F) DT, (G) GP, (H) RF, (I) GB, (J) HGB, (K) XGBoost, (L) CatBoost, (M) LightGBM.

More »

Fig 6 Expand

Table 5.

CO2 emission prediction results.

More »

Table 5 Expand

Fig 7.

CO2 Emission performance metrics of all ML models.

More »

Fig 7 Expand

Fig 8.

Actual versus predicted CO2 emissions plots: (A) Linear regression, (B) Ridge, (C) Lasso, (D) Elastic Net, (E) SVM, (F) DT, (G) GP, (H) RF, (I) GB, (J) HGB, (K) XGBoost, (L) CatBoost, (M) LightGBM.

More »

Fig 8 Expand

Fig 9.

Statistical significance testing (A) Fuel consumption, (B) CO2 prediction.

More »

Fig 9 Expand

Table 6.

CO2 emission prediction comparison with previous studies.

More »

Table 6 Expand

Table 7.

Fuel consumption prediction comparison with previous studies.

More »

Table 7 Expand