Skip to main content
. 2018 Mar 16;9:476. doi: 10.3389/fmicb.2018.00476

Figure 4.

Figure 4

Performance of ERT- and RF-based classifiers in distinguishing between PVPs and non-PVPs. A total of 26 classifiers were evaluated using LOOCV, whose performances in terms of MCC, accuracy, sensitivity, and specificity are shown. (A) ERT-based performance, (B) RF-based performance. Red arrow denotes the final selected models for each ML method.