A Kernel Fisher Discriminant Analysis-Based Tree Ensemble Classifier: KFDA Forest
For practitioners seeking accurate ensemble classifiers, this work offers a novel hybrid method combining KFDA with random forests, though improvements are incremental.
The paper proposes KFDA Forest, a tree ensemble classifier using kernel Fisher discriminant analysis to enhance diversity and accuracy. Experiments on UCI and KEEL datasets show improved classification performance over existing ensemble methods.
In general, an ensemble classifier is more accurate than a single classifier. In this study, we propose an ensemble classifier called the kernel Fisher discriminant analysis forest (KFDA Forest), which is a tree-based ensemble method that applies KFDA. To promote diversity, 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 a rotation, rather than performing 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.