Scientific Reports

Table 5 Statistic metrics obtained by five ML models to forecast the EC parameter in testing 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	0.665	0.676	0.671	0.672
	RMSE	304.606	289.100	317.061	275.404
	MAE	224.062	211.387	241.597	198.092
	RAE	0.807	0.762	0.871	0.714
	MAPE	12.452	11.573	13.049	10.956
	E	0.259	0.333	0.197	0.394
	I_A	0.792	0.799	0.804	0.801
	PI	0.933	0.874	0.996	0.832
ANFIS	R	0.626	0.620	0.650	0.659
	RMSE	350.233	359.110	372.765	320.470
	MAE	258.478	268.127	283.825	241.088
	RAE	0.931	0.966	1.023	0.869
	MAPE	13.954	14.229	14.933	12.863
	E	0.020	-0.030	-0.110	0.180
	I_A	0.764	0.762	0.772	0.790
	PI	0.947	0.968	0.990	0.887
LSSVM	R	0.676	0.676	0.667	0.671
	RMSE	301.595	303.898	309.440	303.767
	MAE	221.156	223.020	225.851	221.441
	RAE	0.797	0.804	0.814	0.798
	MAPE	12.165	12.264	12.415	12.168
	E	0.274	0.263	0.235	0.263
	I_A	0.803	0.800	0.795	0.800
	PI	0.964	0.975	1.000	0.972
GRNN	R	0.620	0.628	0.631	0.616
	RMSE	284.036	288.484	290.054	295.266
	MAE	214.482	221.582	222.083	223.623
	RAE	0.773	0.798	0.800	0.806
	MAPE	11.843	12.247	12.303	12.565
	E	0.356	0.335	0.328	0.304
	I_A	0.747	0.750	0.750	0.724
	PI	0.948	0.969	0.973	1.000
MARS	R	0.630	0.632	0.621	0.648
	RMSE	332.071	327.517	322.743	314.030
	MAE	249.266	247.801	233.385	231.351
	RAE	0.898	0.893	0.841	0.834
	MAPE	13.642	13.405	12.773	12.723
	E	0.119	0.143	0.168	0.213
	I_A	0.764	0.772	0.770	0.786
	PI	0.998	0.966	0.926	0.890

Significant values are in bold.

Back to article page

Search

Advanced search

Quick links