Artificial Neural Networks (ANNs) and Response Surface Methodology (RSM) Approach for Modelling the Optimization of Chromium (VI) Reduction by Newly Isolated Acinetobacter radioresistens Strain NS-MIE from Agricultural Soil

Table 5

Analysis of variance (ANOVA).

Sources	Sum of squares	df	Mean squares	F-value	P>F
Model	5697.40	9	633.04	158.45	< 0.0001	significant
A-Nutrient broth	2116.31	1	2116.31	529.69	< 0.0001
B-pH	1677.11	1	1677.11	419.77	< 0.0001
C-Chromate conc.	1483.92	1	1483.92	371.41	< 0.0001
AB	25.42	1	25.42	6.36	0.0397
AC	0.76	1	0.76	0.19	0.6755
BC	7.40	1	7.40	1.85	0.2158
A^2	298.19	1	298.19	74.63	< 0.0001
B^2	11.06	1	11.06	2.77	0.1401
C^2	52.07	1	52.07	13.03	0.0086
Residual	27.97	7	4.00	4.61
Lack of Fit	21.69	3	7.23		0.0869	Not significant
Pure Error	6.27	4	1.57
					R^2	0.9974
					Adjusted R^2	0.9888

P > F less than 0.05 = statistically significant.