Solution For Nonlinear Multiregression Based On Generalized Choquet Integrals With Pso And Its Application In Estimating Forest Stock Amount

In order to describe the interaction among attributes in information fusion and data mining, a new nonlinear nonnegative multiregression based on Choquet integrals has been proposed.Such a model is a generalization of the traditional linear multiregression, which can be applicated in information fusion and data mining. The crux of using this model is how to determine the unknown parameters,though genetic algorithm has been used for solving this model,it converges slow, and needs a long time.In this paper, we use particle swarm algorithm for solving this model,it not only shortens the solving time, but also gets optimal solution than genetic algorithm.Though the nonlinear nonnegative multiregression based on Choquet integrals has been widely reserched,it has not been applicated in real domains up to now. In order to estimate the forest volume of Saihanba mechanical forest farm, we adopt this modle and applicate it in estimation of the forest volume, the result is satisfying. The application of this model in estimation of the forest volume provides scientific basis for dynamic and scientific management of forest resource.