Table 2.

Evaluation metrics for assessing the results of the reviewed algorithms.

Evaluation Metric	Equation
Mean Absolute Error (MAE)	MAE=$\frac{1}{T}{\sum }_{t=1}^T\mid y_t-{\widehat{y}}_t\mid$
Normalized Absolute Error (NAE)	NAE=$\frac{1}{T}{\sum }_{t=1}^T\frac{\mid y_t-{\widehat{y}}_t\mid }{y_t}$
Maximum Difference (MD)	MD=$\frac{1}{T}\mathit{max}({\sum }_{t=1}^T\left(y_t-{\widehat{y}}_t\right)$
Mean Square Error (MSE)	MSE=$\frac{1}{T}{\sum }_{t=1}^T{\left(y_t-{\widehat{y}}_t\right)}^2$
Laplacian Mean Square Error (LMSE)	LMSE=$\frac{\frac{1}{T}{\sum }_{t=1}^T{\left(y_t-{\widehat{y}}_t\right)}^2}{\frac{1}{T}{\sum }_{t=1}^T{\left(y_t\right)}^2}$
Mean Absolute Percentage Error (MAPE)	MAPE=$\frac{1}{T}{\sum }_{t=1}^T\mid \frac{y_t-{\widehat{y}}_t}{y_t}\mid \ast 100$
Structural Content (SC)	SC=$1-\frac{\frac{1}{T}{\sum }_{t=1}^T{\left(y_t\right)}^2}{\frac{1}{T}{\sum }_{t=1}^T{\left({\widehat{y}}_t\right)}^2}$
Peak Signal to Noise Ratio	PSNR = 10 log 10 $\left(\frac{\mathit{max}{\left(y_t\right)}^2}{\mathit{MSE}}\right)$
Relative Mean Bias Error (rMBE)	rMBE=$\frac{{\sum }_{t=1}^T\left(y_t-{\widehat{y}}_t\right)}{\sum y_t}\ast 100$
Root Mean Square Error (RMSE)	RMSE=$\sqrt{\frac{1}{T}{\sum }_{t=1}^T{\left(y_t-{\widehat{y}}_t\right)}^2}$
Root Mean Square Log Error (RMSLE)	RMSLE=$\sqrt{\frac{1}{T}{\sum }_{t=1}^T{\left(\mathit{log}\left(y_t\right)-\mathit{log}\left({\widehat{y}}_t\right)\right)}^2}$
relative Root Mean Square Error (rRMSE)	rRMSE=$\frac{\sqrt{\frac{1}{T}{\sum }_{t=1}^T{\left(y_t-{\widehat{y}}_t\right)}^2}}{\frac{1}{T}{\sum }_{t=1}^T{y}_t}\ast 100$
Coefficient of determination R squared	$R^2=1-\frac{{\sum }_{t=1}^T{\left(y_t-{\widehat{y}}_t\right)}^2}{{\sum }_{t=1}^T{\left(y_t-\overline{y}\right)}^2}$
Adjusted Coefficient of determination R squared	$R_{\mathit{Adjusted}}^2=1-\frac{T-1}{T-k-1}\frac{{\sum }_{t=1}^T{\left(y_t-{\widehat{y}}_t\right)}^2}{{\sum }_{t=1}^T{\left(y_t-\overline{y}\right)}^2}$
Accuracy (Acc)	$\mathit{Acc}=\frac{\mathit{TP}+\mathit{TN}}{\mathit{TP}+\mathit{TN}+\mathit{FP}+\mathit{FN}}$
Precision (P) or Positive Predictive Value (PPV)	$P=\frac{\mathit{TP}}{\mathit{TP}+\mathit{FP}}$
Recall (R) or Sensitivity	$R=\frac{\mathit{TP}}{\mathit{TP}+\mathit{FN}}$
F-measure	$F-\mathit{measure}=\frac{2\ast \mathit{Precision}\ast \mathit{Recall}}{\mathit{Precision}+\mathit{Recall}}$
Specificity (SPC)	$\mathit{SPC}=\frac{\mathit{TN}}{N}$
Negative Predictive Value (NPV)	$\mathit{NPV}=\frac{\mathit{TN}}{\mathit{TN}+\mathit{FN}}$
Matthews Correlation Coefficient (MCC)	$\mathit{MCC}=\frac{\left(\mathit{TP}\times \mathit{TN}\right)-\left(\mathit{FP}\times \mathit{FN}\right)}{\sqrt{\left(\mathit{TP}+\mathit{FP}\right)\left(\mathit{TP}+\mathit{FN}\right)\left(\mathit{TN}+\mathit{FP}\right)\left(\mathit{TN}+\mathit{FN}\right)}}$