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 6

Central composite design matrix for the three independent variables with the observed and predicted response for chromium reduction by A. radioresistens sp. NS-MIE.

Run	NB conc.	pH	Cr[VI] conc.	Cr reduction [%]
				Observe response	RSM predicted	ANN predicted
1	6.5	7.50	50	63.5663	62.60	63.566
2	10	6.00	75	95.4913	93.18	95.491
3	6.5	6.75	75	71.7557	69.95	69.952
4	6.5	6.00	50	92.8957	94.27	92.896
5	10	6.75	100	59.7617	61.10	59.762
6	3	6.00	75	55.6473	55.61	55.647
7	6.5	6.75	75	68.3594	69.95	69.952
8	6.5	6.00	100	63.3438	64.31	63.344
9	10	6.75	50	86.5347	87.47	86.535
10	3	7.50	75	29.3827	31.69	29.383
11	6.5	6.75	75	69.4251	69.95	69.952
12	3	6.75	50	57.1515	55.81	57.151
13	6.5	6.75	75	70.3893	69.95	69.952
14	6.5	7.50	100	39.4539	38.08	39.454
15	6.5	6.75	75	69.8326	69.95	69.952
16	3	6.75	100	28.6329	27.70	28.633
17	10	7.50	75	59.1438	59.18	59.144