Online active learning of decision trees with evidential data. (April 2016)

• Record Type: Journal Article
• Authors: Ma, Liyao; Destercke, Sébastien; Wang, Yong
• Is Part Of: Pattern recognition. Volume 52(2016:Apr.)
• Page Start: 33
• Page End: 45
• Publication Date: 2016-04
• Subjects: Decision tree -- Active learning -- Evidential likelihood -- Uncertain data -- Belief functions; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.10.014
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Learning from uncertain data has attracted increasing attention in recent years. In this paper, we propose a decision tree learning method that can not only handle uncertain data, but also reduce epistemic uncertainty by querying the most valuable uncertain instances within the learning procedure. Specifically, we use entropy intervals extracted from the evidential likelihood to query uncertain training instances when needed, with the goal to improve the selection of the splitting attribute. Experimental results under various conditions confirm the interest of the proposed approach. Abstract : 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.