Table 3.
Investigated parameters for the training process of the RF (see Fig. 6 for a single regression tree) for the system listed in Table 1.
| Ntrees | 200, 400, 800 |
|---|---|
| Nmss | 2, 4, 8 |
| Nmsl | 1, 2, 4 |
| Nmax samples | 50 000, 100 000, 200 000, 300 000, 400 000 |
| Nmax features | 1,  |
Notes. We vary the number of trees, Ntrees, the minimum number of samples required to split an internal node, Nmss, the minimum number of samples required to be in a leaf node, Nmsl, the size of the bootstrapped data set, Nmax samples, and the maximum number of features, Nmax features, considered to create a root or internal node.
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.