An Undersampling Method Approaching the Ideal Classification Boundary for Imbalance Problems
Source abstract
Abstract
Data imbalance is a common problem in most practical classification applications of machine learning, and it may lead to classification results that are biased towards the majority class if not dealt with properly. An effective means of solving this problem is undersampling in the borderline area; however, it is difficult to find the area that fits the classification boundary. In this paper, we present a novel undersampling framework, whereby the clustering of samples in the majority class is conducted and segmentation is then performed in the boundary area according to the clusters obtained; this enables a better shape that fits the classification boundary to be obtained via the performance of random sampling in the borderline area of these segments. In addition, we hypothesize that there exists an optimal number of classifiers to be integrated into the method of ensemble learning that utilizes multiple classifiers that have been obtained via sampling to promote the algorithm. After passing the hypothesis test, we apply the improved algorithm to the newly developed method. The experimental results show that the proposed method works well.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Imbalanced Data Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Key Laboratory of Offshore Oil and Gas Exploitation, Beijing 100028, China
CNOOC Research Institute Ltd., Beijing 100028, China
School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, China
Funding
Open Fund Project of the National Key Laboratory of Offshore Oil and Gas Development
References (40)
Show source-provided references
1. Salah Al-Deen, S., Castillo, P.A., and Faris, H. (2022). Cost-sensitive metaheuristic optimization-based neural network with ensemble learning for financial distress prediction. Appl. Sci., 12.10.3390/app12146918 ↗
2. Alruily, M., El-Ghany, S.A., Mostafa, A.M., Ezz, M., and El-Aziz, A.A. (2023). A-tuning ensemble machine learning technique for cerebral stroke prediction. Appl. Sci., 13.10.3390/app13085047 ↗
3. Competition-driven multimodal multiobjective optimization and its application to feature selection for credit card fraud detection10.1109/TSMC.2022.3171549 ↗
4. Liu, Y., Zhou, J., Zhang, D., Wei, S., Yang, M., and Gao, X. (2024). Fault Diagnosis Method of Box-Type Substation Based on Improved Conditional Tabular Generative Adversarial Network and AlexNet. Appl. Sci., 14.10.3390/app14073112 ↗
5. Drop loss for person attribute recognition with imbalanced noisy-labeled samples10.1109/TCYB.2022.3173356 ↗
6. Subspace-based minority oversampling for imbalance classification10.1016/j.ins.2022.11.108 ↗
7. Neighbourhood-based undersampling approach for handling imbalanced and overlapped data10.1016/j.ins.2019.08.062 ↗
8. A novel two-phase clustering-based under-sampling method for imbalanced classification problems10.1016/j.eswa.2022.119003 ↗
9. Learn Stable MRI Under-sampling Pattern with Decoupled Sampling Preference10.1109/TCI.2024.3361773 ↗
10. Van Hulse, J., Khoshgoftaar, T.M., and Napolitano, A. (2010, January 12–14). A novel noise filtering algorithm for imbalanced data. Proceedings of the Ninth International Conference on Machine Learning and Applications, Washington, DC, USA.10.1109/ICMLA.2010.9 ↗
11. SMOTE–IPF: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering10.1016/j.ins.2014.08.051 ↗
12. A noise-filtered under-sampling scheme for imbalanced classification10.1109/TCYB.2016.2606104 ↗
13. Sampling technique for noisy and borderline examples problem in imbalanced classification10.1016/j.asoc.2023.110361 ↗
14. Zhang, J., Wang, T., Ng, W.W., Zhang, S., and Nugent, C.D. (2019, January 7–10). Undersampling near decision boundary for imbalance problems. Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC), Kobe, Japan.10.1109/ICMLC48188.2019.8949290 ↗
15. Relevant information undersampling to support imbalanced data classification10.1016/j.neucom.2021.01.033 ↗
16. Cluster-based under-sampling approaches for imbalanced data distributions10.1016/j.eswa.2008.06.108 ↗
17. Clustering-based undersampling in class-imbalanced data10.1016/j.ins.2017.05.008 ↗
18. Under-sampling class imbalanced datasets by combining clustering analysis and instance selection10.1016/j.ins.2018.10.029 ↗
19. Li, J., Wang, H., Song, C., Han, R., and Hu, T. (2021, January 17–19). Research on Hierarchical Clustering Undersampling and Random Forest Fusion Classification Method. Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing (PIC), Shanghai, China.10.1109/PIC53636.2021.9687089 ↗
20. Unstructured borderline self-organizing map: Learning highly imbalanced, high-dimensional datasets for fault detection10.1016/j.eswa.2021.116028 ↗
21. A boosting-aided adaptive cluster-based undersampling approach for treatment of class imbalance problem10.4018/IJDWM.2020070104 ↗
22. DBIG-US: A two-stage under-sampling algorithm to face the class imbalance problem10.1016/j.eswa.2020.114301 ↗
23. Tahfim, S.A.S., and Chen, Y. (2024). Comparison of Cluster-Based Sampling Approaches for Imbalanced Data of Crashes Involving Large Trucks. Information, 15.10.3390/info15030145 ↗
24. Two-step ensemble under-sampling algorithm for massive imbalanced data classification10.1016/j.ins.2024.120351 ↗
25. Feng, W., Huang, W., and Ren, J. (2018). Class imbalance ensemble learning based on the margin theory. Appl. Sci., 8.10.3390/app8050815 ↗
26. Ensembles of (α)-Trees for Imbalanced Classification Problems10.1109/TKDE.2012.255 ↗
27. Sleep spindle detection using RUSBoost and synchrosqueezed wavelet transform10.1109/TNSRE.2020.2964597 ↗
28. VMD-Based Ensembled SMOTEBoost for Imbalanced Multi-Class Rotor Mass Imbalance Fault Detection and Diagnosis Under Industrial Noise10.1007/s42417-023-00920-w ↗
29. A cluster-based SMOTE both-sampling (CSBBoost) ensemble algorithm for classifying imbalanced data10.1038/s41598-024-55598-1 ↗
30. Undersampling of approaching the classification boundary for imbalance problem10.1002/cpe.7586 ↗
31. Incremental weighted ensemble broad learning system for imbalanced data10.1109/TKDE.2021.3061428 ↗
32. Equalization ensemble for large scale highly imbalanced data classification10.1016/j.knosys.2022.108295 ↗
33. Learning from imbalanced data10.1109/TKDE.2008.239 ↗
34. Radial-based undersampling for imbalanced data classification10.1016/j.patcog.2020.107262 ↗
35. Optimal BRA based electric demand prediction strategy considering instance-based learning of the forecast factors10.1002/2050-7038.12967 ↗
36. The use of the area under the ROC curve in the evaluation of machine learning algorithms10.1016/S0031-3203(96)00142-2 ↗
37. Powers, D.M.W. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv.
38. Logistic discrimination based on G-mean and F-measure for imbalanced problem10.3233/IFS-162150 ↗
39. DBSCAN revisited, revisited: Why and how you should (still) use DBSCAN10.1145/3068335 ↗
40. Support vector clustering