Research of the Improved Adaboost Algorithm Based on Unbalanced Data

A large of Non-equilibrium data exist in the real world, because of the traditional classification methods based on assumptions of class balance and different categories misclassification the same costs as well as the evaluation criteria based on the accuracy of the overall sample classification, resulting in the classification of non-equilibrium data has not apply. Classification for unbalanced data, Adaboost algorithm and its adaptability in the classification of non-equilibrium data were analyzed in this paper first, followed by proposed an improved method for their classification in a non-equilibrium defects in the data, and finally proceed effectiveness analysis to improve methods through the experiment.