Research Article

A Hybrid Approach for Modular Neural Network Design Using Intercriteria Analysis and Intuitionistic Fuzzy Logic

Table 10

Results from the simulations.

N:DescriptionNumber of the inputsNumber of weight coefficients

1Module 1—2, 3, 4, 5, 6, 9
Module 2—1, 7, 8
90.76580.87961.6721350
2Module 1—2, 3, 4, 5, 6, 9
Module 2—7, 8 (without 1)
80.76580.86961.6584315
3Module 1—2, 3, 4, 5, 6, 9
Module 2—1, 8 (without 7)
80.76580.92771.7492315
4Module 1—2, 3, 4, 5, 6, 9 
Module 2—1, 7 (without 8)
80.76581.58262.8488315
5Module 1—2, 3, 4, 5, 6, 9
Module 2—8 (without 1, 7)
70.76580.87561.6626280
6Module 1—2, 3, 4, 5, 6, 9
Module 2—7 (without 1, 8)
70.76581.71903.0898280
7Module 1—2, 3, 4, 5, 6, 9
Module 2—1 (without 7, 8)
70.76581.63782.9400280