Identification of general fuzzy measures by genetic algorithms based on partial information

This study develops an identification procedure for general fuzzy measures using genetic algorithms. In view of the difficulty in data collection in practice, the amount of input data is simplified through a sampling procedure concerning attribute subsets, and the corresponding detail design is adapted to the partial information acquired by the procedure. A specially designed genetic algorithm is proposed for better identification, including the development of the initialization procedure, fitness function, and three genetic operations. To show the applicability of the proposed method, this study simulates a set of experimental data that are representative of several typical classes. The experimental analysis indicates that using genetic algorithms to determine general fuzzy measures can obtain satisfactory results under the framework of partial information.