Fig. 9.
Download original image
Feature importance of the XGBoost model trained on the first set of parameters from Table 1 (left) and on all parameters (right). The training hyperparameters are 10, 0.1, and 50, respectively, for the maximum depth of trees, the learning rate, and the maximum number of trees. Features are ordered from top to bottom in order of decreasing importance.
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.