Learning from Data Stream Based on Random Projection and Hoeffding Tree Classifier

Luong

Dang

et al. 2020

Pattern Recognition

Self Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Section: Related Work 21 Ensemble Methodsmentioning

confidence: 99%

Ensemble Selection based on Classifier Prediction Confidence

Luong

Dang

et al. 2020

Pattern Recognition

Self Cite

“…In the literature, besides the practical applications of ensemble methods in many areas, research on ensemble methods can be divided into three aspects: information for the trained classifiers of a given learning task can be inferred so as to obtain the optimal combining weights of the trained classifiers. Moreover, several ensemble systems were developed for different learning paradigms such as incremental learning [30][31][32], semisupervised learning [33], and multi-label learning [34,35]. For instance, Pham et al [31] combined random projections and Hoeffding tree to construct an incremental online ensemble learning system.…”

Section: Ensemble Methodsmentioning

confidence: 99%

“…Moreover, several ensemble systems were developed for different learning paradigms such as incremental learning [30][31][32], semisupervised learning [33], and multi-label learning [34,35]. For instance, Pham et al [31] combined random projections and Hoeffding tree to construct an incremental online ensemble learning system. Krawczyk and Cano [32] incrementally learnt a threshold for each arrived instance in the online heterogeneous ensemble system.…”

Section: Ensemble Methodsmentioning

confidence: 99%

Combining heterogeneous classifiers via granular prototypes

Pham

et al. 2018

Applied Soft Computing

Self Cite

In this study, a novel framework to combine multiple classifiers in an ensemble system is introduced. Here we exploit the concept of information granule to construct granular prototypes for each class on the outputs of an ensemble of base classifiers. In the proposed method, uncertainty in the outputs of the base classifiers on training observations is captured by an interval-based representation. To predict the class label for a new observation, we first determine the distances between the output of the base classifiers for this observation and the class prototypes, then the predicted class label is obtained by choosing the label associated with the shortest distance. In the experimental study, we combine several learning algorithms to build the ensemble system and conduct experiments on the UCI, colon cancer, and selected CLEF2009 datasets. The experimental results demonstrate that the proposed framework outperforms several benchmarked algorithms including two trainable combining methods, i.e.

“…As in batch learning, trees often need to be used in an ensemble framework to get high performance [5], one would do the same with the online setting. Hoeffding trees are now mainly used as base learners in online meta-learning methods (see for example [30]).…”

Section: Related Workmentioning

confidence: 99%

A lossless online Bayesian classifier

Sharma

et al. 2019

Information Sciences

Self Cite

We are living in a world progressively driven by data. Besides mining big data which cannot be altogether stored in the main memory as required by traditional offline methods, the problem of learning rare data that can only be collected over time is also very prevalent. Consequently, there is a need of online methods which can handle arriving data and offer the same accuracy as offline methods. In this paper, we introduce a new lossless online Bayesianbased classifier which uses the arriving data in a 1-by-1 manner and discards each data right after use. The lossless property of our proposed method guarantees that it can reach the same prediction model as its offline counterpart regardless of the incremental training order. Experimental results demonstrate its superior performance over many well-known state-of-theart methods in the literature.