Skip to main content
. 2018 Oct 15;8:15264. doi: 10.1038/s41598-018-33654-x

Figure 3.

Figure 3

Training process of 10-fold cross-validation on balance set (A) and imbalance set (B). In 10-fold cross-validation, we calculate the mean MCC of each epoch and the standard error of MCC. For balance set, the highest average MCC is 0.74 and the highest standard error is 0.15. For imbalance set, the highest average MCC is 0.73 and the highest standard error is 0.20.