Table 5.

The comparison performance of ANN using selected sensors.

No.	Sensor selection	MSE	Gradient	Sample	Target			ANN Output (Averaged)			Accuracy
					T1	T2	T3	O1	O2	O3
1	S23, S31, S1, S2, S4	8.2038 × 10−9	0.1074	G12	1	0	0	0.9983	0.0045	0.0070	100%
				G22	0	1	0	0.0001	0.9999	0.0070	100%
				G32	0	0	1	0.0001	0.0000	0.9999	100%
2	S23 and S31	8.9927 × 10−8	0.00246	G12	1	0	0	0.9803	0.0125	0.0070		100%
				G22	0	1	0	0.0010	0.9999	0.0009		100%
				G32	0	0	1	0.6203	0.0000	0.3797		37.18%