Measure optimized cost-sensitive neural network ensemble for multiclass imbalance data learning
- Peng Cao
- Dazhe Zhao
- Osmar R. Zaiane, University of Alberta (Database)
The performance of traditional classification algorithms can be limited on imbalanced datasets. In recent years, the imbalanced data learning problem has drawn significant interest. In this work, we focus on designing modifications to neural network, in order to appropriately tackle the problem of multiclass imbalance. We propose a hybrid method that combines two ideas: diverse random subspace ensemble learning with evolutionary search, to improve the performance of neural network on multiclass imbalanced data. An evolutionary search technique is utilized to optimize the misclassification cost under the guidance of imbalanced data measures. Moreover, the diverse random subspace ensemble employs the minimum overlapping mechanism to provide diversity so as to improve the performance of the learning and optimization of neural network. We have demonstrated experimentally using UCI datasets that our approach can achieve better result than state of-the-art methods for imbalanced data.
Citation
P. Cao, D. Zhao, O. Zaiane. "Measure optimized cost-sensitive neural network ensemble for multiclass imbalance data learning". International Conference on Hybrid Intelligent Systems, Hammamet, Tunisia, pp 35-40, December 2013.Keywords: | imbalanced data, cost sensitive learning, ensemble classifier, swarm intelligence |
Category: | In Conference |
Web Links: | Webdocs |
BibTeX
@incollection{Cao+al:13, author = {Peng Cao and Dazhe Zhao and Osmar R. Zaiane}, title = {Measure optimized cost-sensitive neural network ensemble for multiclass imbalance data learning}, Pages = {35-40}, booktitle = {International Conference on Hybrid Intelligent Systems}, year = 2013, }Last Updated: November 14, 2019
Submitted by Sabina P