Optimisation of culture conditions for gesho (Rhamnus prinoides.L) callus differentiation using Artificial Neural Network-Genetic Algorithm (ANN-GA) Techniques

Applied Biological Chemistry

Table 2 CCD based combinations used for ANN modelling and response from RSM data

Run	A: Agar concentration	B: Light duration	C: Culture temperature	D: Relative humidity	(Actual value) Rate of differentiation	Predicted Value
Run	(Y1, %)	(Y2, h/d)	(Y3, °C)	(Y4, %)	(A, %)	(P, %)
1	0.9	16	20	80	77.23	83.25
2	0.9	16	36	80	77.15	81.65
3	1.1	13	28	70	79.01	89.15
4	0.5	10	36	60	77.09	78.63
5	0.5	16	20	80	76.98	79.48
6	0.7	13	12	70	76.02	72.96
7	0.9	10	20	80	77.92	81.52
8	0.9	10	36	80	76.42	80.59
9	0.9	10	20	60	78.93	81.45
10	0.7	13	28	70	84.75	79.58
11	0.7	13	28	50	76.03	72.89
12	0.9	10	36	60	78.56	80.63
13	0.9	16	36	60	76.74	76.52
14	0.7	13	28	90	74.56	84.56
15	0.7	7	28	70	78.42	72.89
16	0.7	13	28	70	84.99	81.24
17	0.5	16	36	60	78.32	84.56
18	0.7	13	44	70	76.99	83.56
19	0.5	10	36	80	75.28	79.52
20	0.7	13	28	70	84.53	71.84
21	0.3	13	28	70	78.64	86.56
22	0.7	13	28	70	84.87	78.65
23	0.9	16	20	60	75.95	78.26
24	0.5	16	20	60	76.8	90.56
25	0.7	19	28	70	78.91	74.15
26	0.7	13	28	70	84.15	79.06
27	0.5	10	20	60	77.34	83.85
28	0.7	13	28	70	84.58	63.96
29	0.5	16	36	80	78.59	72.45
30	0.5	10	20	80	76	82.96