Skip to main content

Table 10 Types of performance measures used in method evaluation for the 39 papers which has quantitative performance values and their respective formulas, papers and total number of papers, where TP = true positive, TN = true negative, FP = false positive, FN = false negative, \(x_{i}\) = observed value or ground truth of sample i, \({\hat{x}}_i\) = predicted value of sample i and n = number of samples

From: Sensor data quality: a systematic review

Evaluation metric Formula Papers Total
Recall \(\frac{TP}{TP+FN}\) [31, 35, 36, 38, 39, 42, 45, 48, 51, 57, 58, 60, 78] 13
False positive rate (FPR) \(\frac{FP}{TN+FP}\) [31, 33, 38,39,40, 44, 47, 54, 57,58,59, 71] 12
False negative rate (FNR) \(\frac{FN}{TP+FN}\) [40, 44, 47, 48, 54, 71] 6
Precision \(\frac{TP}{TP+FP}\) [35, 36, 38, 51, 78] 5
Accuracy \(\frac{TP+TN}{TP+TN+FP+FN}\) [37, 48, 51, 79] 4
F-score \(2 \times \frac{precision \times recall}{precision + recall}\) [35, 36] 2
Matthew’s correlation coefficient (MCC) \(\frac{TP \times TN - FP \times FN}{\sqrt{(TP+FP)(TP+FN)(TN+FP)(TN+FN)}}\) [65] 1
Regression metrics
 Root mean squared error (RMSE) \(\sqrt{MSE}\) [46, 62, 64, 66] 4
 Mean squared error (MSE) \(\frac{1}{n}\sum _{i=1}^n(x_i - {\hat{x}}_i)^2\) [72, 76] 2
 Mean absolute error (MAE) \(\frac{1}{n}\sum _{i=1}^{n}|x_i - {\hat{x}}_i|\) [61, 67] 2
 Mean relative error (MRE) \(\frac{1}{n}\sum _{i=1}^{n}\frac{|x_i - {\hat{x}}_i|}{x_i}\) [30, 67] 2