A new neural network approach to evaluate the potential of public works

In this paper, a method of multi-objective synthetic evaluation based on artificial neural networks is presented. First, a new kind of membership, which changes evaluation values with different dimensions and different kinds of indexes into relative membership with no dimensions, not only emphasizes on the principle " reward good and penalize bad" but also makes it easy for us to train neural networks to be used in this paper. Second, how to make decision on the weights of indexes is discussed and the difficulties are analyzed. Third, the principle of multi-objective synthetic evaluation based on artificial neural networks is described in detail, and applied to a real synthetic assessment of synthetic benefits of 16 public works in China. The results are satisfactory. In the end of this paper, the characteristics of the method proposed in this paper are analyzed. This method is successfully applied in some other decision field in our country. The application reveals the method here is superior to the conventional method of system modeling.