Analysis of Credal-C4.5 for classification in noisy domains

作者：

Highlights：

• The robustness of Credal-C4.5 in noisy domains is analyzed. Credal-C4.5 depends on the ‘s’ parameter.

• The relation between noise level and value of s is studied in terms of accuracy.

• A large experimental study is carried out varying the values of s.

• The correct selection of s can improve notably the results for each noise level.

摘要

•The robustness of Credal-C4.5 in noisy domains is analyzed. Credal-C4.5 depends on the ‘s’ parameter.•The relation between noise level and value of s is studied in terms of accuracy.•A large experimental study is carried out varying the values of s.•The correct selection of s can improve notably the results for each noise level.

论文关键词：Imprecise probabilities,Imprecise Dirichlet model,Uncertainty measures,Credal decision trees,C4.5 algorithm,noisy data

论文评审过程：Received 30 November 2015, Revised 24 May 2016, Accepted 25 May 2016, Available online 31 May 2016, Version of Record 9 June 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.05.035