Advances in Artificial Neural Systems / 2016 / Article / Tab 4

Research Article

A State-Based Sensitivity Analysis for Distinguishing the Global Importance of Predictor Variables in Artificial Neural Networks

Table 4

Resultant mean values for input ( to ) and output () variables in the hypothetical database derived in state-based sensitivity analysis (SBSA) and local sensitivity analysis (local SA), for instance, when the mean value of lies within a distinct “state” along its distribution range.

state valueSBSALocal SA

1
2
3−1.83−0.550.12−0.440.04−1.500.010.16−0.270.03−1.29
4−1.37−0.010.96−0.201.03−1.100.010.16−0.270.03−0.95
5−0.91−2.16−1.56−1.14−0.45−1.610.010.16−0.270.03−0.62
6−0.46−0.280.030.03−0.70−0.280.010.16−0.270.03−0.30
70.000.44−0.35−0.750.95−0.090.010.16−0.270.030.04
80.460.591.040.20−0.040.750.010.16−0.270.030.37
90.911.34−0.72−0.44−0.701.300.010.16−0.270.030.69
10
111.83−0.28−1.280.49−0.200.830.010.16−0.270.031.36
12