탐지 결과를 평가하기 위한 척도

TP(True Positive), FP(False Positive), FN(False Negative), TN(True Negative)

* TPR (True Positive Ratio)

- TPR = TP / (TP + FN)

* FPR (False Positive Ratio)

- FPR = FP / (FP + TN)

* Accuracy(%)

- (TP+TN) / (TP + FP + FN + TN) * 100

아래는 다른 문서에서 확인 한 설명

The results of classification will be represented in a confusion matrix composed of tp (true positive), fn (false negative), tn (true negative), and fp (false positive), respectively. We define the precision and recall as: Precision =tp/(tp+fp), Recall=tp/(tp+fn). Then, the results are evaluated by calculating F-measure as F=2*(Precision*recall)/(Precision+Recall).