Online active learning of decision trees with evidential data

作者：

Highlights：

• Active belief decision trees are learned from uncertain data modelled by belief functions.

• A query strategy is proposed to query the most valuable uncertain instances while learning decision trees.

• To deal with evidential data, entropy intervals are extracted from the evidential likelihood.

• Experiments with UCI data illustrate the robustness of proposed approach to various kinds of uncertain data.

摘要

Highlights•Active belief decision trees are learned from uncertain data modelled by belief functions.•A query strategy is proposed to query the most valuable uncertain instances while learning decision trees.•To deal with evidential data, entropy intervals are extracted from the evidential likelihood.•Experiments with UCI data illustrate the robustness of proposed approach to various kinds of uncertain data.

论文关键词：Decision tree,Active learning,Evidential likelihood,Uncertain data,Belief functions

论文评审过程：Received 2 April 2015, Revised 28 September 2015, Accepted 19 October 2015, Available online 30 October 2015, Version of Record 24 December 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.10.014