K-L absolute information dispersion clustering model and application in evaluating water-saving irrigation program

摘要

In view of the complexity of indexes for evaluating water-saving irrigation program, to resolve the incompatibility of the results of evaluating water-saving irrigation program, and to raise the distinguishment of the model of evaluating water-saving irrigation program, application of projection data distribution and normal distribution difference as projection index, an effective and general model, named as K-L absolute information dispersion clustering model was suggested. The Real Coding based on Accelerating Genetic Algorithm was used to find the best projective direction, and the data of the best projective direction to research the level of the influence of each factor to water-saving irrigation program, the classification results according with the fact were got, which provided the decision reference for water-saving irrigation program.