“…While impressive (near-perfect) results on the TPEHGDB dataset are reported in many studies [10,20,33,2,16,19,12,27,1,34,21,29,18,17,11,15], these results should be interpreted cautiously as their evaluation methodology is based on applying over-sampling strategies before data partitioning. All these studies apply over-sampling in order to make the distribution of classes more uniform.…”