Advances in fuzzy integration for pattern recognition
Fuzzy Sets and Systems - Special issue on fuzzy methods for computer vision and pattern recognition
Using neural networks to determine Sugeno measures by statistics
Neural Networks
Fuzzy Measure Theory
Hi-index | 0.00 |
This paper will use fuzzy integral to structure the diagnostic model of gestational diabetes mellitus. The Sugeno measure is obtained by training of BP neural network. The BP neural network is easy to get into local optimum, so the algorithm of simulated annealing is used to optimize the BP neural network, and it will obtain an approximate global optimal solution. In this diagnostic model, there are two key factors. One is the degree of fit that the degrees of evidential support for attribute that diagnostic object is gestational diabetes mellitus. The other is the importance of attribute itself. The instances of diabetes illuminate that the method is effective.