Skip to main content

Table 3 Results of the comparison test between the computer-operated Yolo-4 model and the embedded-operated Yolo-4 model for 100 randomly selected test data set images

From: Convolutional neural network-based vocal cord tumor classification technique for home-based self-prescreening purpose

Platform

TP

FP

FN

TN

Acc

Pre

Rec

Spe

F1

Computer

89

9

18

391

0.9467

0.9082

0.8318

0.9775

0.8683

Embedded

87

9

21

391

0.9409

0.9063

0.8056

0.9775

0.8529

  1. TP true-positive, FP false-positive, FN false-negative, TN true-negative, Acc accuracy, Pre precision, Rec recall, Spe specificity, F1 F1-score