基于粗糙集理论的决策树生成与剪枝方法-电路与系统专业论文.docxVIP

AbstraetData Abstraet Data Mining(i．e．Knowledge Discovery from database)is a process to mine available， credible，valid and comprehensible pattem from large—scale data in an intelligent and automatic way．Classification is one of the most important directions in Data Mining and has been widely used in many fields such as medical diagnosis，climate predict，credit validate， client distinguish，fraud discriminate and so on． Decision tree is a regular classification model．Comparing with other classification models，it is concise and convenient to be transformed into rules，which are simple for people to understand．And the classification accuracy of decision tree is beRer or not worse than other models．Due to all these advantages，decision tree has gotcen a wide application． Rough set theory proposed by Professor Z．Pawlak is an effective tool to deal with vagueness，imprecise，incomplete and uncertain data，which it has gained fruitful progress after 20 years’development． The whole work of this dissertation is mainly on the approach of constructing and pruning decision tree based on Rough Set Theory： 1)Research on the inducing approach ofdecision tree．Pawlak rough set theory can’t deal well with noisy data for its property of rigorous precision，and neither does the decision tree induction approach based on it．The tree constructed by Pawlak rough set theory is easy to overfit the training data and can’t instruct prediction effectively．This paper improved the Pawlak Rough Set Theory based decision tree inducing approach according to Variable precision rough set theory．Variable precision rough set theory permit equivalence classes to be classified into the approximation space wrongly in some extent，which insures the tree constructed by it Call prohibit the noisy data perfectly comparing with the one constructed by Pawlak rough set theory, 2)Research on the pruning approach ofdecision tree．It is important to prune the decision tree for enhancing the generalize property of it．According