Variable fuzzy model based on combined weights and its application to risk assessment for flood control engineering
Wang Ben-de · Dalian Ligong Daxue xuebao · 2009
Considering the disadvantages of using subjective weights in the former studies for the risk assessment of the flood control engineering system,the variable fuzzy pattern recognition model based on the combination of the subjective and objective weights is developed.Projection pursuit(PP) method is employed to calculate the objective weights in the model,and the information entropy is considered in the PP object function.The model′s reliability is improved due to using variable fuzzy sets model for the projection value calculation.The combined weights formulas are obtained based on the minimum discriminating information principle.The case shows that subjective and objective weights can be taken into account comprehensively in the presented model,and the identification result is stable and valid.