Analysis and extension of decision trees based on imprecise probabilities: Application on noisy data
作者：
Highlights：
• A Decision Tree method based on imprecise probabilities is analyzed.
• A new model is presented where all input variables are processed with imprecision.
• Experiments on data sets with different levels of general noise are carried out.
• The new method obtains smaller trees and better results than the original method.
• The new method outperforms the classic ones on data set with general noise.
摘要
•A Decision Tree method based on imprecise probabilities is analyzed.•A new model is presented where all input variables are processed with imprecision.•Experiments on data sets with different levels of general noise are carried out.•The new method obtains smaller trees and better results than the original method.•The new method outperforms the classic ones on data set with general noise.
论文关键词：Imprecise probabilities,Imprecise Dirichlet model,Uncertainty measures,Credal Decision Trees,Noisy data
论文评审过程：Available online 18 October 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.09.050
