Scientific Reports

Table 4 Statistic metrics obtained by five ML models to forecast the EC parameter in training stage.

From: An improved adaptive neuro fuzzy inference system model using conjoined metaheuristic algorithms for electrical conductivity prediction

Model	Criteria	Combination
Model	Criteria	Combo 1	Combo 2	Combo 3	Combo 4
ANFIS-A-DEPSO	R	0.848	0.845	0.846	0.844
	RMSE	353.197	356.313	355.442	359.698
	MAE	243.342	253.611	244.956	248.578
	RAE	0.449	0.468	0.452	0.459
	MAPE	12.960	14.165	13.460	12.950
	E	0.719	0.714	0.715	0.709
	I_A	0.914	0.909	0.910	0.905
	PI	0.977	1.000	0.983	0.982
ANFIS	R	0.841	0.841	0.836	0.841
	RMSE	360.181	360.099	366.059	360.440
	MAE	250.811	250.091	257.408	252.690
	RAE	0.463	0.461	0.475	0.466
	MAPE	13.740	13.631	14.596	13.908
	E	0.708	0.708	0.698	0.707
	I_A	0.908	0.908	0.905	0.908
	PI	0.984	0.982	1.000	0.987
LSSVM	R	0.825	0.826	0.829	0.827
	RMSE	376.503	375.911	373.261	375.117
	MAE	257.907	257.315	254.815	256.712
	RAE	0.476	0.475	0.470	0.474
	MAPE	14.637	14.510	14.377	14.506
	E	0.681	0.682	0.686	0.683
	I_A	0.895	0.895	0.897	0.895
	PI	1.000	0.998	0.994	0.997
GRNN	R	0.790	0.811	0.813	0.804
	RMSE	417.344	398.072	396.565	408.553
	MAE	292.164	278.826	277.396	289.653
	RAE	0.539	0.514	0.512	0.534
	MAPE	16.998	16.151	16.068	16.941
	E	0.608	0.643	0.646	0.624
	I_A	0.848	0.868	0.870	0.855
	PI	1.000	0.981	0.979	0.996
MARS	R	0.844	0.834	0.837	0.832
	RMSE	357.725	368.062	364.990	369.822
	MAE	245.850	252.034	256.522	258.810
	RAE	0.454	0.465	0.473	0.478
	MAPE	13.273	13.793	13.944	14.456
	E	0.712	0.695	0.700	0.692
	I_A	0.910	0.903	0.905	0.902
	PI	0.973	0.986	0.992	1.000

Significant values are in bold.

Back to article page

Search

Advanced search

Quick links