Multi-view forests based on Dempster-Shafer evidence theory: a new classifier ensemble method

In this paper, a method to construct ensembles of tree-structured classifiers using multi-view learning instead of feature subset selection is proposed. An essential requirement to train an effective classifier ensemble is the diversity among the base individual classifiers. In order to construct diverse individual classifiers, it is assumed that the object to be classified is represented through multiple feature sets (views). Different views of the data can then be combined to improve the accuracy of the learning task. Multi-view Forests have been examined on a benchmark data set of 3D-object recognition based on 2D camera images. Results show that multi-view learning can improve the performance of the individual classifiers and the whole ensemble, and thus promoting the use of multi-view forests.

[1]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[2]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[3]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[4]  Sanjoy Dasgupta,et al.  Hybrid Hierarchical Clustering: Forming a Tree From Multiple Views , 2005 .

[5]  Günther Palm,et al.  Hierarchical Neural Networks Utilising Dempster-Shafer Evidence Theory , 2006, ANNPR.

[6]  Galina L. Rogova,et al.  Combining the results of several neural network classifiers , 1994, Neural Networks.

[7]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Rebecca Fay,et al.  Feature selection and information fusion in hierarchical neural networks for iterative 3D-object recognition , 2007 .

[9]  Arthur P. Dempster,et al.  A Generalization of Bayesian Inference , 1968, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[10]  E. Mandler,et al.  Combining the Classification Results of Independent Classifiers Based on the Dempster/Shafer Theory of Evidence , 1988 .

[11]  C. J. Whitaker,et al.  Ten measures of diversity in classifier ensembles: limits for two classifiers , 2001 .

[12]  Günther Palm,et al.  Tree-Structured Support Vector Machines for Multi-class Pattern Recognition , 2001, Multiple Classifier Systems.

[13]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[14]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.