A hybrid ensemble and evolutionary algorithm for imbalanced classification and its application on bioinformatics. (June 2022)

• Record Type: Journal Article
• Authors: Zhang, Yongqing; Lin, Meng; Yang, Yihan; Ding, Chunli
• Is Part Of: Computational biology and chemistry. Volume 98(2022)
• Publication Date: 2022-06
• Subjects: Imbalanced classification -- Evolutionary algorithm -- Ensemble learning -- Bioinformatics; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2022.107646
• Languages: English
• ISSNs: 1476-9271

Abstract

Abstract: Imbalanced data classification is the fundamental problem of data mining. Relevant researchers have proposed many solutions to solve the problem, such as sampling and ensemble learning methods. However, random under-sampling is easy to lose representative samples, and ensemble learning does not use the correlation information between pieces in the data set. Therefore, we proposed a H ybrid A daptive sampling with B agging C lassifier(HABC). Specifically, we calculated the adaptive sampling rate according to the characteristics of the data set. We then performed density-based under-sampling and over-sampling on the original data set according to the sampling rate. Further, the sampled data subset was sent to the Bagging classifier, and the classifier was employed to predict the unknown data set. In addition, the multi-objective particle swarm optimization algorithm was combined to optimize the prediction result. Extensive experiments based on UCI, KEEL, and three bioinformatics datasets show that our proposed method is better than state-of-the-art algorithms. Graphical Abstract: ga1 Highlights: Designed a density-based under-sampling algorithm to generate a valid subset. Designed an adaptive sampling rate algorithm according to the imbalanced characteristics. Designed an ensemble framework that utilizes the sample's similarity and multi-objective optimization to improve results.