Title: Interval type-2 fuzzy inference systems as integration methods in modular neural networks for multimodal biometry and its optimisation with genetic algorithms
Authors: Denisse Hidalgo, Oscar Castillo, Patricia Melin
Addresses: Tijuana Institute of Technology, Tijuana BC, Mexico. ' Tijuana Institute of Technology, Tijuana BC, Mexico. ' Tijuana Institute of Technology, Tijuana BC, Mexico
Abstract: In this paper a comparative study of fuzzy inference systems as methods of integration in Modular Neural Networks (MNNs) for multimodal biometry is presented. These methods of integration are based on type-1 and type-2 fuzzy logic. Also, the fuzzy systems are optimised with simple genetic algorithms. First, we considered the use of type-1 fuzzy logic and later the approach with type-2 fuzzy logic. The fuzzy systems were developed using genetic algorithms to handle fuzzy inference systems with different membership functions, like the triangular, trapezoidal and Gaussian; since these algorithms can generate the fuzzy systems automatically. Then the response integration of the MNN was tested with the optimised fuzzy integration systems. The comparative study of type-1 and type-2 fuzzy inference systems was made to observe the behaviour of the two different integration methods of MNNs for multimodal biometry.
Keywords: interval type-2 fuzzy logic; modular neural networks; genetic algorithms; multimodal biometry; fuzzy inference systems; biometrics.
International Journal of Biometrics, 2008 Vol.1 No.1, pp.114 - 128
Published online: 04 Jun 2008 *Full-text access for editors Access for subscribers Purchase this article Comment on this article