Table 3. Performance values (Mean ± Standard deviation) of generic pain estimation model for different sensor and model combinations across all subjects.

Sensor	Model	Performance
		MAE	RMSE
EDA	Linear Regression	0.99 ± 0.15	1.18 ± 0.18
	SVR	0.93 ± 0.19	1.15 ± 0.21
	Neural Networks	0.95 ± 0.17	1.15 ± 0.19
	Random Forest	0.96 ± 0.18	1.15 ± 0.20
	KNN	0.98 ± 0.16	1.17 ± 0.18
	XGBoost	0.95 ± 0.17	1.13 ± 0.19
ECG	Linear Regression	1.16 ± 0.10	1.35 ± 0.12
	SVR	1.15 ± 0.16	1.36 ± 0.18
	Neural Networks	1.17 ± 0.11	1.37 ± 0.12
	Random Forest	1.17 ± 0.12	1.36 ± 0.13
	KNN	1.19 ± 0.09	1.39 ± 0.11
	XGBoost	1.16 ± 0.10	1.34 ± 0.12
EMG	Linear Regression	1.20 ± 0.05	1.39 ± 0.06
	SVR	1.20 ± 0.00	1.41 ± 0.00
	Neural Networks	1.22 ± 0.05	1.41 ± 0.06
	Random Forest	1.21 ± 0.05	1.40 ± 0.06
	KNN	1.23 ± 0.05	1.43 ± 0.06
	XGBoost	1.20 ± 0.04	1.39 ± 0.05
Early fusion of EDA+ECG+ EMG	Linear Regression	0.98 ± 0.17	1.17 ± 0.19
	SVR	0.96 ± 0.19	1.16 ± 0.21
	Neural Networks	1.01 ± 018	1.22 ± 0.19
	Random Forest	0.95 ± 0.18	1.14 ± 0.19
	KNN	1.02 ± 0.15	1.21 ± 0.17
	XGBoost	0.94 ± 0.18	1.13 ± 0.20