A novel method for creating an optimized ensemble classifier by introducing cluster size reduction and diversity
Date
2022
Authors
Jan, Z.
Munoz, J.
Ali, A.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
IEEE Transactions on Knowledge and Data Engineering, 2022; 34(7):3072-3081
Statement of Responsibility
Conference Name
Abstract
In this paper, a new method is proposed for creating an optimized ensemble classifier. The proposed method mitigates the issue of class imbalances by partitioning the input data into its various data classes. The partitions are then clustered incrementally to generate a pool of class pure data clusters. The generated data clusters are then balanced by adding samples from all classes which are closest to the cluster centroid. In this manner all generated data clusters are balanced and classifiers trained on such a data cluster are unbiased as well. This creates a diverse input space for training of base classifiers. The pool of clusters is then utilized to train a set of diverse base classifiers to generate the base classifier pool. The pool of classifiers is then treated as a combinatorial problem of optimization and an evolutionary algorithm is incorporated. The proposed approach generates an optimized ensemble classifier that can not only achieve the highest classification accuracy but also has a lower component size as well. The proposed approach is tested on 31 benchmark datasets from UCI machine learning repository and results are compared with existing state-of-the-art ensemble classifiers as well.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2020 IEEE