Skip to main content
. 2022 Jun 6;13:821233. doi: 10.3389/fmicb.2022.821233

Figure 3.

Figure 3

Comparison of model performance in terms of accuracy (A) and AUC (B) for with different channel sizes and dropouts. Multiple comparison tests on the different units were applied in the models using one-way ANOVA, following the post-hoc Tukey HSD test for paired difference with a p-value < 0.05. Different letters indicate a significant difference.