The CFA results showed satisfactory fit indices at each wave: chi square ([chi square])/degrees of freedom (df) ratio = 2.27, standardized

root mean square residual (SRMR) = .064,

root mean square error of approximation (RMSEA) = .077, goodness-of-fit index (GFI) = .90, comparative fit index (CFI) = .95.

Advantages of the mean absolute error (MAE) over the

root mean square error (RMSE) in assessing average model performance.

In this study, the mean square error (MSE),

root mean square error (RMSE), normalized

root mean square error (NRMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were calculated using the following equations, which are the indexes of forecasting accuracy:

Within the scope of time domain parameters, SDNN (standard deviation of NN Intervals), SDANN (standard deviation of NN in All 5-Minute Segments), SDNN index (mean of five minute standard deviation of NN intervals), RMSSD (

Root Mean Square of Successive NN Interval Differences) and PNN50 (proportion of NN50) were evaluated.

Based on this, Chi-square ([chi square])/degrees of freedom (df) were calculated to be 2.807, standardized

root mean square residual (SRMR) to be 0.093, adjusted goodness of fit index (AGFI) to be 0.854, comparative fit index (CFI) to be 0.879, and

root mean square error of approximation (RMSEA) to be 0.078 (Table 2).

Modeling the break eliminates forecast bias, reduces

root mean square forecast error, and significantly increases the signaling power of the PMI.

In each band, the high protruding frequency is extracted as the feature, and

root mean square (RMS) value for these protruding frequencies are used for fault detection.

The

Root Mean Square Residual (RMR) index between 0 and 1 and the root mean squared error approximation (RMSEA) index lower than 0.05 are considered to be an indicator of good fit (28-30).

RMSE:

Root Mean Square Error; NRMSE: Normalized

Root Mean Square Error; BIAS: BIAS index; r: correlation coefficient.

It was performed as follows: (1) 90% of the calibration dataset samples were used to form the calibration model, and the remaining 10% samples were used to validate this model, and the procedure was repeated by 10 times; (2) the

root mean square error of cross-validation (RMSECV) was then calculated as follows:

Caption: Figure 2:

Root mean square error for the AOA in degrees vs.

We chose to use

root mean square residual (RMR), Standardized

Root Mean Square Residual (SRMR) and

Root Mean Square Error of Approximation (RMSEA) for a number of reasons.