Not Logged In

A PSO-based Cost-Sensitive Neural Network for Imbalanced Data Classification

Full Text: bdm2013.pdf PDF

Learning from imbalanced data is an important and common problem. Many methods have been proposed to address and attempt to solve the problem, including sampling and cost-sensitive learning. This paper presents an effective wrapper approach incorporating the evaluation measure directly into the objective function of cost-sensitive neural network to improve the performance of classification, by simultaneously optimizing the best pair of feature subset, intrinsic structure parameters and misclassification costs. The optimization is based on Particle Swarm Optimization. Our designed method can be applied on the binary class and multi-class classification. Experimental results on various standard benchmark datasets show that the proposed method is effective in comparison with commonly used sampling techniques.

Citation

P. Cao, D. Zhao, O. Zaiane. "A PSO-based Cost-Sensitive Neural Network for Imbalanced Data Classification". Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), April 2013.

Keywords: classification with Class imbalance, Cost-sensitive learning, Neural network, Particle swarm intelligence
Category: In Conference

BibTeX

@incollection{Cao+al:PAKDD13,
  author = {Peng Cao and Dazhe Zhao and Osmar R. Zaiane},
  title = {A PSO-based Cost-Sensitive Neural Network for Imbalanced Data
    Classification},
  booktitle = {Pacific-Asia Conference on Knowledge Discovery and Data Mining
    (PAKDD)},
  year = 2013,
}

Last Updated: January 13, 2020
Submitted by Sabina P

University of Alberta Logo AICML Logo