Enhanced Bagging (eBagging): A Novel Approach for Ensemble Learning

Creative Commons License

Tüysüzoğlu G., Birant D.

INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, vol.17, no.4, pp.515-528, 2020 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 17 Issue: 4
  • Publication Date: 2020
  • Doi Number: 10.34028/iajit/17/4/10
  • Journal Name: INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Arab World Research Source, Computer & Applied Sciences
  • Page Numbers: pp.515-528
  • Keywords: Bagging, boosting, classification algorithms, machine learning, random forest, supervised learning, CLASSIFICATION, CLASSIFIERS
  • Dokuz Eylül University Affiliated: Yes

Abstract

Bagging is one of the well-known ensemble learning methods, which combines several classifiers trained on different subsamples of the dataset. However, a drawback of bagging is its random selection, where the classification performance depends on chance to choose a suitable subset of training objects. This paper proposes a novel modified version of bagging, named enhanced Bagging (eBagging), which uses a new mechanism (error-based bootstrapping) when constructing training sets in order to cope with this problem. In the experimental setting, the proposed eBagging technique was tested on 33 well-known benchmark datasets and compared with both bagging, random forest and boosting techniques using well-known classification algorithms: Support Vector Machines (SVM), decision frees (C4.5), k-Nearest Neighbour (kNN) and Naive Bayes (NB). The results show that eBagging outperforms its counterparts by classifying the data points more accurately while reducing the training error.