Performance Analysis of Extracted Rule-Base Multivariable Type-2 Self-Organizing Fuzzy Logic Controller Applied to Anesthesia
Table 5
Mean and standard deviation of steady state errors and control stabilities of type-1/interval type-2/zSlice general type-2 SOFLC using extracted rule-base with results of Wilcoxon signed-rank test.
Controller performance
Noise strength
Type
Stage-1 MR
Stage-1 BP
Stage-2 MR
Stage-2 BP
Steady state errors
0.1
1
0.0181 (±) 0.0092*
1.6288 (±) 1.5593*
0.0515 (±) 0.0296
2.5869 (±) 2.5605*
Interval
0.0069 (±) 0.0012*
0.0919 (±) 0.0087
0.0066 (±) 0.0005*
0.1292 (±) 0.0045*
General
0.0018 (±) 0.0008
0.1268 (±) 0.0106*
0.0056 (±) 0.0007
0.0416 (±) 0.0062*
0.2
1
0.0154 (±) 0.0122
2.1513 (±) 1.4063*
0.0730 (±) 0.0032*
4.5476 (±) 0.2598*
Interval
0.0052 (±) 0.0022
0.1452 (±) 0.0146
0.0044 (±) 0.0009*
0.0839 (±) 0.0100*
General
0.0045 (±) 0.0013
0.0677 (±) 0.0842*
0.0079 (±) 0.0012
0.0433 (±) 0.0159
Control stabilities
0.1
1
0.0239 (±) 0.0077
0.6005 (±) 0.3110*
0.0147 (±) 0.0014
0.5133 (±) 0.0462
Interval
0.0083 (±) 0.0007
0.0046 (±) 0.0004
0.0078 (±) 0.0006
0.0043 (±) 0.0003
General
0.0099 (±) 0.0011
0.0052 (±) 0.0009
0.0099 (±) 0.0005
0.0059 (±) 0.0006
0.2
1
0.0237 (±) 0.0079*
0.9731 (±) 0.5516*
0.0171 (±) 0.0009
1.0247 (±) 0.0833
Interval
0.0134 (±) 0.0012
0.0094 (±) 0.0013
0.0126 (±) 0.0011
0.0083 (±) 0.0011
General
0.0170 (±) 0.0042
0.0187 (±) 0.0183
0.0148 (±) 0.0011
0.0130 (±) 0.0020
Reject hypothesis: extracted rule-base is better than expert derived rule-base.