Open Access
Table 4
Properties of the final RF regressor ML-model properties chosen to be trained on.
| Model features | Type | Properties | Notes |
|---|---|---|---|
| Max. depth = 25, | Training a chain regressor | ||
| Model type | Random Forest Regression | Max. features=0.9, | connects the non-independent target |
| Number of estimators=100 | parameter to one another | ||
| Data scaling | Max-min normalization | Inputs and outputs are scaled | Aids the model to learn the problem |
| Validation method | K-fold cross-validation | k=10 with data shuffle | Ensures the model gets trained on every single data point |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.