Research On Bays Classification Arithmetic And Application On Tunnel Damage Prediction

Our capabilities of both generating and collecting data have been increasing rapidly in the last several decades. In the situation, data mining technique is developed and it has been investigated by more and more researchers. As the important technique of data mining, classification technique has been applied at large.This paper makes a detail study of Bayes classification arithmetic and improved the Naive Bayes Classification: combining Naive Bayes Classification, Weighted Naive Bayes and TAN arithmetic and proposing a new Weighted Mixed Bayes model. The characteristics of the arithmetic as followed: First of all, dividing attribute set by using Hierarchies which can solve the problem that it is difficult to training Bayes net model due to a great number of attributes in traditional Bayes net arithmetic. Secondly, it decreases the independence assumption of Bayes classification by using TAN arithmetic to training attributes in each attribute subset. Thirdly, introducing weighted function among attribute subsets which makes the arithmetic applied in complicated relational data and improving the practicability and accuracy of the method. At the same time, through data experiment the advantages and validity are proved.In addintion, prevention control projection tunnel damage is so complicated that the method adopted presently which depends on manual basis lacks of systematism. After study on background knowledge about tunnel and damage, this paper employs techniques of data mining on historical tunnel data, so the inherent law can be excavated and the damage rank can be predicted. The technques rangs from data pretreatment to classification based on Weighted Mixed Bayes model and get the result of classification according to experiment on tunnel data of Chengdu Railway Bureau. The result shows the final model is successful. Finally this paper also gives some advices to railway departments about damage prevention and cure.