TABLE 5.

Neurofuzzy logic model Mean Square Error (MSE), train set R², ANOVA parameters for training [f-ratio, degrees of freedom (df1: model and df2: total), and f-critical value for α = 0.05].

Outputs	MSE	Train set R2 (%)	f-ratio	df1	df2	f-critical (α = 0.05)	Critical factors
SN	0.0055	89.495	9.030	16	33	3.558	Na+ × MoO22– SO42– × I– NH4+ × NO3– × BO3–
SL	0.0107	80.063	10.350	9	33	4.255	Fe2+ K+ Mg2+ BO3– PO43–
LA	0.0159	75.629	17.378	5	33	5.382	NO3– × Na+ Cl–
SQ	0.0050	92.998	26.563	11	33	3.975	Fe2+ K+ × SO42– BO3– NO3–
BC	0.0069	89.346	16.771	11	33	3.975	PO43– × NH4+
							SO4–2
H	0.0173	75.250	11.289	7	33	4.675	Cl– × I–SO42– × BO3–

Critical factors (significant inputs) computed for each output are bolded. SN, shoot number; SL, shoot length; LA, leaf area; SQ, shoot quality; BC, basal callus; and H, hyperhydricity.