Table 2.

Comparison of prediction performance for the different ANN architectures in three different cases of difficulty based on the liver-to-liver variance, noise and drift in the measurement. The selection of input frequencies and hyperparameters for the best prediction performance of the different ANN architectures is provided in the rows below the prediction performances. The last row presents the best prediction performance when all 70 frequencies are used as input to the ANN. RMSEP=root mean square error of prediction, RMSEC=root mean square error of calibration, both having units of ischemia duration in hours.

Case	Easy			Medium			Hard
Liver variance	5 %			5 %			20 %
Noise	0			10			30
Drift	0			100			100
Drift direction	None			Increasing			Both
Training examples	100			100			100
Best performance	FNN	LSTM	2LSTM	FNN	LSTM	2LSTM	FNN	LSTM	2LSTM
Mean RMSEP	0.124	0.016	0.017	0.173	0.029	0.026	0.256	0.079	0.066
Std RMSEP	0.025	0.003	0.009	0.044	0.003	0.012	0.044	0.013	0.015
Mean RMSEC	0.112	0.014	0.015	0.175	0.026	0.021	0.256	0.037	0.038
Std RMSEC	0.029	0.005	0.007	0.029	0.006	0.009	0.029	0.006	0.018
Frequencies	70	3	7	70	7	3	70	3	3
Hidden layer size	25	25	5	5	5	25	2	25	25
l2 regularization	0.1	0.001	0.001	0.001	0.001	0.001	0.001	0.001	0.001
Training epochs	NA	500	500	NA	500	500	NA	500	500
Minibatch size	NA	32	32	NA	32	32	NA	32	16
Mean RMSEP (freq=70)	0.124	0.056	0.022	0.173	0.073	0.035	0.256	0.142	0.106