CBR-PSO: cost-based rough particle swarm optimization approach for high-dimensional imbalanced problems

Aydogan E. K., ÖZMEN M., Delice Y.

NEURAL COMPUTING & APPLICATIONS, vol.31, no.10, pp.6345-6363, 2019 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 31 Issue: 10
  • Publication Date: 2019
  • Doi Number: 10.1007/s00521-018-3469-2
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.6345-6363
  • Keywords: Multiple classifier system, Attribute reduction, High-dimensional imbalanced datasets, Particle swarm optimization, Rough set theory, ATTRIBUTE REDUCTION, DATA-SETS, NEURAL-NETWORKS, CLASSIFICATION, PREDICTION, ALGORITHM, SMOTE
  • Kayseri University Affiliated: Yes


Datasets, which have a considerably larger number of attributes compared to samples, face a serious classification challenge. This issue becomes even harder when such high-dimensional datasets are also imbalanced. Recently, such datasets have attracted the interest of both industry and academia and thereby have become a very attractive research area. In this paper, a new cost-sensitive classification method, the CBR-PSO, is presented for such high-dimensional datasets with different imbalance ratios and number of classes. The CBR-PSO is based on particle swarm optimization and rough set theory. The robustness of the algorithm is based on the simultaneously applying attribute reduction and classification; in addition, these two stages are also sensitive to misclassification cost. Algorithm efficiency is examined in publicly available datasets and compared to well-known attribute reduction and cost-sensitive classification algorithms. The statistical analysis and experiments showed that the CBR-PSO can be better than or comparable to the other algorithms, in terms of MAUC values.