A KERNEL FISHER DISCRIMINANT ANALYSIS-BASED TREE ENSEMBLE CLASSIFIER: KFDA FOREST

Authors

  • Donghwan Kim Korea University
  • Seung Hwan Park Chungnam National University
  • Jun-Geol Baek Korea University

DOI:

https://doi.org/10.23055/ijietap.2018.25.5.3703

Keywords:

Classification, Ensemble Classifier, Decision Trees, Kernel Fisher Discriminant Analysis, Rotation Forest

Abstract

In general, an ensemble classifier is more accurate than a single classifier. In this study, we propose an ensemble classifier called kernel Fisher discriminant analysis forest (KFDA Forest). This is a tree-based ensemble method that applies KFDA. To promote diversity, a bootstrap is used and variable sets are randomly divided into K subsets. KFDA is performed on each subset to increase classification accuracy. KFDA maximizes the distance between classes while minimizing the distance within classes. KFDA can also be applied to classification problems in a nonlinear data structure using the kernel trick because it can transform the input space into a kernel feature space, commonly named rotation, rather than a dimensionality reduction. Because new feature axes and KFDA projections are parallel, decision trees are used as a base classifier. To compare the proposed method with existing ensemble methods, we apply these to real datasets from the UCI and KEEL repositories.

Author Biographies

Seung Hwan Park, Chungnam National University

Department of Mechanical Engineering

Jun-Geol Baek, Korea University

School of Industrial Management Engineering

Published

2019-01-03

How to Cite

Kim, D., Park, S. H., & Baek, J.-G. (2019). A KERNEL FISHER DISCRIMINANT ANALYSIS-BASED TREE ENSEMBLE CLASSIFIER: KFDA FOREST. International Journal of Industrial Engineering: Theory, Applications, and Practice, 25(5). https://doi.org/10.23055/ijietap.2018.25.5.3703