1Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China 2Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan 430081, China 3Precision Manufacturing Institute, Wuhan University of Science and Technology, Wuhan 430081, China
[Objective] This paper proposes a borderline oversampling method based on the k-nearest neighbor algorithm (KNN) and Deep Gaussian Mixture Model (DGMM) to address the classifier bias due to data imbalance. [Methods] Firstly, we used the KNN algorithm to obtain the borderline minority samples in the training set. Secondly, we constructed a DGMM for the minority samples. Next, we applied the DGMM in reverse to generate the oversampling samples that conform to the distribution characteristics of the borderline minority samples. Finally, we used the three sigma guidelines to remove noise samples. We repeated the process until no outlier samples were generated. [Results] The proposed method improved the AUC and G-mean up to 8.62% and 12.99%, respectively. The corresponding average increased by 3.51% and 4.93%. [Limitations] The parameter optimization method for DGMM needs further improvement. [Conclusions] The proposed method can better address the problem of imbalanced data.
张海宾, 肖涵, 易灿灿, 袁锐. 基于KNN和深度高斯混合模型的边界过采样方法*[J]. 数据分析与知识发现, 2023, 7(5): 116-122.
Zhang Haibin, Xiao Han, Yi Cancan, Yuan Rui. A Novel Borderline Over-Sampling Method Based on KNN and Deep Gaussian Mixture Model for Imbalanced Data. Data Analysis and Knowledge Discovery, 2023, 7(5): 116-122.
Zhao C S, Xin Y, Li X F, et al. A Heterogeneous Ensemble Learning Framework for Spam Detection in Social Networks with Imbalanced Data[J]. Applied Sciences, 2020, 10(3): 936.
doi: 10.3390/app10030936
[2]
Ghorbani M, Kazi A, Baghshah M S, et al. RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data[J]. Medical Image Analysis, 2022, 75: 102272.
doi: 10.1016/j.media.2021.102272
(Xiao Lianjie, Gao Mengrui, Su Xinning. An Under-sampling Ensemble Classification Algorithm Based on Fuzzy C-Means Clustering for Imbalanced Data[J]. Data Analysis and Knowledge Discovery, 2019, 3(4): 90-96.)
[4]
Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: Synthetic Minority Over-Sampling Technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357.
doi: 10.1613/jair.953
[5]
Nekooeimehr I, Lai-Yuen S K. Adaptive Semi-unsupervised Weighted Oversampling (A-SUWO) for Imbalanced Datasets[J]. Expert Systems with Applications, 2016, 46: 405-416.
doi: 10.1016/j.eswa.2015.10.031
[6]
Han H, Wang W Y, Mao B H. Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning[C]// Advances in Intelligent Computing. 2005.
[7]
Bunkhumpornpat C, Sinapiromsaran K, Lursinsap C. Safe-Level-SMOTE: Safe-Level-Synthetic Minority Over-Sampling Technique for Handling the Class Imbalanced Problem[C]// Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining. 2009: 475-482.
[8]
Pradipta G A, Wardoyo R, Musdholifah A, et al. Radius-SMOTE: A New Oversampling Technique of Minority Samples Based on Radius Distance for Learning from Imbalanced Data[J]. IEEE Access, 2021, 9: 74763-74777.
doi: 10.1109/ACCESS.2021.3080316
[9]
Douzas G, Bacao F. Geometric SMOTE a Geometrically Enhanced Drop-in Replacement for SMOTE[J]. Information Sciences, 2019, 501(C): 118-135.
[10]
Yang S J, Cha K J. GMOTE: Gaussian Based Minority Oversampling Technique for Imbalanced Classification Adapting Tail Probability of Outliers[OL]. arXiv Preprint, arXiv: 2105. 03855.
[11]
Cheng K, Zhang C, Yu H L, et al. Grouped SMOTE with Noise Filtering Mechanism for Classifying Imbalanced Data[J]. IEEE Access, 2019, 7: 170668-170681.
doi: 10.1109/ACCESS.2019.2955086
[12]
Kamalov F, Denisov D. Gamma Distribution-Based Sampling for Imbalanced Data[J]. Knowledge-Based Systems, 2020, 207: 106368.
doi: 10.1016/j.knosys.2020.106368
(Xiao Han, Li Yourong, Lv Yong. Failure Recognition Alogrithm Based on QDFD and GMM[J]. Journal of Vibration Engineering, 2008, 21(1): 79-83.)
[14]
van den Oord A, Schrauwen B. Factoring Variations in Natural Images with Deep Gaussian Mixture Models[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. 2014: 3518-3526.
[15]
Viroli C, McLachlan G J. Deep Gaussian Mixture Models[J]. Statistics and Computing, 2019, 29(1): 43-51.
doi: 10.1007/s11222-017-9793-z
[16]
Yakowitz S. Nearest-Neighbour Methods for Time Series Analysis[J]. Journal of Time Series Analysis, 1987, 8(2): 235-247.
doi: 10.1111/j.1467-9892.1987.tb00435.x
[17]
Alcalá-Fdez J, Sánchez L, García S, et al. KEEL: A Software Tool to Assess Evolutionary Algorithms for Data Mining Problems[J]. Soft Computing, 2009, 13(3): 307-318.
doi: 10.1007/s00500-008-0323-y
[18]
Mazini M, Shirazi B, Mahdavi I. Anomaly Network-Based Intrusion Detection System Using a Reliable Hybrid Artificial Bee Colony and AdaBoost Algorithms[J]. Journal of King Saud University - Computer and Information Sciences, 2019, 31(4): 541-553.
doi: 10.1016/j.jksuci.2018.03.011
[19]
García S, Herrera F. Evolutionary Undersampling for Classification with Imbalanced Datasets: Proposals and Taxonomy[J]. Evolutionary Computation, 2009, 17(3): 275-306.
doi: 10.1162/evco.2009.17.3.275
pmid: 19708770
