Oversampling framework based on sample subspace optimization with accelerated binary particle swarm optimization for imbalanced classification

被引:2
|
作者
Li, Junnan [1 ]
机构
[1] Chongqing Ind Polytech Coll, Sch Artificial Intelligence & Big Data, Chongqing 401120, Peoples R China
基金
中国国家自然科学基金;
关键词
Class-imbalanced classification; Oversampling methods; Instance selection; Sample subspace optimization; Particle swarm optimization; K-MEANS; SMOTE; DBSCAN;
D O I
10.1016/j.asoc.2024.111708
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In response to the need to generate synthetic minority class samples to extend minority classes, the SMOTE-based oversampling methods have been favored for class-imbalanced classification. They usually generate unnecessary noise when training data are not well separated. Although filtering-based oversampling methods are recognized as effective solutions for addressing noise generation through employing specific noise filters based on instance selection methods to remove suspicious noise, they suffer from the following issues: a) noise filters heavily rely on strong assumptions, causing low robustness to different datasets; b) noise filters are specially designed for a specific oversampling method, and are not easily extended to others; and c) noise filters have a relatively high time consumption. To address noise generation while overcoming the above issues a)-c), an oversampling framework based on sample subspace optimization with accelerated binary particle swarm optimization (OFSSO-ABPSO) is proposed. OF-SSO-ABPSO is a wrapping framework compatible with almost all the oversampling methods. First, in the framework, a SMOTE-based method is used to generate synthetic minority class samples. Second, a novel accelerated binary particle swarm optimization (ABPSO) algorithm with a new search space reduction strategy, a new particle update mechanism, and a new fitness function is proposed. Third, a novel ABPSO-based sample subspace optimization (SSO-ABPSO) method is proposed and used as a noise filter to remove suspicious noise from the training set and synthetic minority class samples. Experiments prove that, a) OF-SSO-ABPSO can improve 6 representative SMOTE variations by addressing noise generation, and b) OF-SSOABPSO outperforms 7 state-of-the-art filtering-based oversampling methods.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Binary particle swarm optimization in classification
    Cervantes, A
    Galván, I
    Isasi, P
    NEURAL NETWORK WORLD, 2005, 15 (03) : 229 - 241
  • [2] GPSO: A FRAMEWORK FOR OPTIMIZATION OF GENETIC PROGRAMMING CLASSIFIER EXPRESSIONS FOR BINARY CLASSIFICATION USING PARTICLE SWARM OPTIMIZATION
    Jabeen, Hajira
    Baig, Abdul Rauf
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2012, 8 (1A): : 233 - 242
  • [3] Entropy based Binary Particle Swarm Optimization and classification for ear detection
    Ganesh, Madan Ravi
    Krishna, Rahul
    Manikantan, K.
    Ramachandran, S.
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2014, 27 : 115 - 128
  • [4] A particle swarm optimization based simultaneous learning framework for clustering and classification
    Liu, Ruochen
    Chen, Yangyang
    Jiao, Licheng
    Li, Yangyang
    PATTERN RECOGNITION, 2014, 47 (06) : 2143 - 2152
  • [5] Binary Accelerated Particle Swarm Algorithm (BAPSA) for discrete optimization problems
    Zahra Beheshti
    Siti Mariyam Shamsuddin
    Siti Sophiayati Yuhaniz
    Journal of Global Optimization, 2013, 57 : 549 - 573
  • [6] Binary Accelerated Particle Swarm Algorithm (BAPSA) for discrete optimization problems
    Beheshti, Zahra
    Shamsuddin, Siti Mariyam
    Yuhaniz, Siti Sophiayati
    JOURNAL OF GLOBAL OPTIMIZATION, 2013, 57 (02) : 549 - 573
  • [7] Solving the imbalanced data classification problem with the particle swarm optimization based support vector machine
    Xu, Zhenyuan
    Watada, Juilzo
    Wu, Mingnan
    Ibrahim, Zuwarie
    Khalid, Marzuki
    IEEJ Transactions on Electronics, Information and Systems, 2014, 134 (06) : 788 - 795
  • [8] An oversampling framework for imbalanced classification based on Laplacian eigenmaps
    Ye, Xiucai
    Li, Hongmin
    Imakura, Akira
    Sakurai, Tetsuya
    NEUROCOMPUTING, 2020, 399 : 107 - 116
  • [9] The application of binary accelerated particle swarm optimization method to unconstrained binary quadratic problems
    Lin, Geng
    Guan, Jian
    INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS & STATISTICS, 2014, 52 (08): : 55 - 61
  • [10] SECURE STEGANOGRAPHY BASED ON BINARY PARTICLE SWARM OPTIMIZATION
    Guo Yanqing Kong Xiangwei You Xingang(School of Electronic and Information Engineering
    Journal of Electronics(China), 2009, 26 (02) : 285 - 288