HECMI: Hybrid Ensemble Technique for Classification of Multiclass Imbalanced Data

  • Kiran BhowmickEmail author
  • Utsav B. ShahEmail author
  • Medha Y. Shah
  • Pratik A. Parekh
  • Meera Narvekar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 863)


Imbalanced data is a problem which is observed in many real-world applications. Although a lot of research is focused on achieving a solution to handle this problem, most of them assume binary classes. However, occurrence of multiple classes in most of the applications is not uncommon. Multiclass classification with imbalanced data poses additional challenges. This paper proposes a hybrid ensemble approach for classification of multiclass imbalanced data (HECMI). A hybrid of data based and algorithm based approach is proposed to deal with the imbalance and multiple classes. The ensemble created focuses on misclassified instances that are added to the partitioned dataset. HECMI proves to be more accurate than traditional algorithms.


Multiclass Ensemble Imbalance Classification 


  1. 1.
    Haixiang, G., Yijing, L., Shang, J., Mingyun, G., Yuanyue, H., Bing, G.: Learning from class-imbalanced data: review of methods and applications. Int. J. Expert Syst. Appl., 220–239. Elsevier (2017)Google Scholar
  2. 2.
    Elaheh, A., Kantardzic, M., Sethi, T.S.: A partial labeling framework for multi-class imbalanced streaming data. In: International Joint Conference on Neural Networks (IJCNN), IEEE, Anchorage, AK, USA (2017)Google Scholar
  3. 3.
    Wang, S., Minku L., Yao X.: Dealing with multiple classes in online class imbalance learning. In: International Joint Conference on Artificial Intelligence (IJCAI-16), pp. 2118–2124. IEEE, New York, USA (2016)Google Scholar
  4. 4.
    Rafiez, A., Raziff, A., Sulaiman, M.N., Mustapha, N., Perumal, T: Single classifier, OvO, OvA and RCC multiclass classification method in handheld based smartphone gait identification. In: AIP Conference Proceedings (2017)Google Scholar
  5. 5.
    Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., Herrera, F.: A review on ensembles for the class imbalance problem: bagging, boosting, and hybrid-based approaches. IEEE Trans. Syst. MAN Cybern. 42, 463–484. IEEE (2011)Google Scholar
  6. 6.
    Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., Herrera, F.: An overview of ensemble methods for binary classifiers in multi-class problems: experimental study on one-vs-one and one-vs-all schemes. Int. J. Pattern Recogn., pp. 1761–1776 Elsevier (2011)Google Scholar
  7. 7.
    Fernández, A., Jesus, M.J., Herrera, F.: Multi-class imbalanced data-sets with linguistic fuzzy rule based classification systems based on pairwise learning. In: Hüllermeier, E., Kruse, R., Hoffmann, F. (eds.) Computational Intelligence for Knowledge-Based Systems Design. IPMU 2010. Lecture Notes in Computer Science, vol. 6178. Springer, Berlin, Heidelberg (2010)Google Scholar
  8. 8.
    Jeatrakul, P., et al.: Enhancing classification performance of multi-class imbalanced data using the OAA-DB algorithm. In: IJCNN (2012)Google Scholar
  9. 9.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. (JAIR) 16, 321–357 (2002)CrossRefGoogle Scholar
  10. 10.
    Alejo, R., Sotoca, J.M., Valdovinos, R.M., Casa˜n, G.A.: The multi-class imbalance problem: cost functions with modular and non-modular neural networks. In: Wang, H., Shen, Y., Huang, T., Zeng, Z. (eds.) The Sixth International Symposium on Neural Networks (ISNN 2009). Advances in Intelligent and Soft Computing, vol. 56. Springer, Berlin, Heidelberg (2009)Google Scholar
  11. 11.
    Zhou, Z.H., Liu, X.Y.: On multi-class cost-sensitive learning. In: AAAI (2009)Google Scholar
  12. 12.
    Krawczyk, B.: Cost-sensitive one-vs-one ensemble for multi-class imbalanced data. In: IJCNN, IEEE, Canada (2016)Google Scholar
  13. 13.
    Yijing, L., Haixiang, G., Xiao, L., Yanan, L., Jinling, L.: Adapted ensemble classification algorithm based on multiple classifier system and feature selection for classifying multi-class imbalanced data. Int. J. Knowl. Based Syst. 94, 88–104. Elsevier (2016)Google Scholar
  14. 14.
    Wei, L., Zhe, L., Chu, J.,: Adaptive ensemble under sampling-boost: a novel learning framework for imbalanced data. Int. J. Syst. Softw. 132, 272–282. Elsevier (2017)Google Scholar
  15. 15.
    Ortigosa-Hernández, J., Inza, I., Lozano, J.A.: Measuring the class-imbalance extent of multi-class problems. Int. J. Pattern Recogn. Lett. 98, 32–38. Elsevier (2017)Google Scholar
  16. 16.
    Yuan, X., Xie, L., Abouelenien, M.: A regularized ensemble framework of deep learning for cancer detection from multi-class, imbalanced training data. Int. J. Pattern Recogn. 77, 160–172. Elsevier (2018)Google Scholar
  17. 17.
    Bi, J., Zhang, C.: An empirical comparison on state-of-the-art multi-class imbalance learning algorithms and a new diversified ensemble learning scheme. Int. J. Knowl. Based Syst. 94. Elsevier (2018)Google Scholar
  18. 18.
    García, S., Zhang, Z.L., Altalhi, A., Alshomrani, S., Herrera, F.: Dynamic ensemble selection for multi-class imbalanced datasets. Int. J. Inf. Sci., vol. 445–446, pp. 22–37. Elsevier (2018)Google Scholar
  19. 19.
    Fernández-Baldera, A., Buenaposada, J., Baumela, L.: BAdaCost: Multi-class Boosting with Costs. Int. J. Pattern Recogn. 79, 467–479. Elsevier (2018)Google Scholar
  20. 20.
    Dua, D., Taniskidou, K.E.: UCI machine learning repository ( Irvine, CA: University of California, School of Information and Computer Science (2017)

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Dwarkadas J. Sanghvi College of EngineeringMumbaiIndia

Personalised recommendations