Open Access

Table 6

The proposed model has the best performance for all evaluation metrics.

  LDA RCCV ETC RFC XGBoost
Metric Tuned Default Tuned Default Tuned Defaul Tuned Default Tuned Default
Precision 0.882 0.831 0.841 0.801 0.860 0.831 0.931 0.842 0.936 0.852
Recall 0.879 0.829 0.843 0.80 0.857 0.829 0.921 0.829 0.936 0.843
F1-score 0.880 0.829 0.838 0.799 0.856 0.829 0.923 0.830 0.936 0.843
Train ACC 0.927 0.946 0.884 0.895 0.986 0.10 0.998 0.10 0.993 0.10
Test ACC 0.879 0.829 0.843 0.80 0.857 0.829 0.921 0.829 0.936 0.843

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.