Chaotic multi-swarm whale optimizer boosted support vector machine for medical diagnosis

• Published in: Applied soft computing Vol. 88; p. 105946
• Main Authors: Wang, Mingjing, Chen, Huiling
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2020
• Subjects: Medical diagnosis; Model selection; Multi-swarm; Support vector machine; Whale optimization algorithm; Multi-swarm; Whale optimization algorithm; Support vector machine; Medical diagnosis; Model selection
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2019.105946

Support vector machine (SVM) is a widely used pattern classification method that its classification accuracy is greatly influenced by both kernel parameter setting and feature selection. Therefore, in this study, to perform parameter optimization and feature selection simultaneously for SVM, we propose an improved whale optimization algorithm (CMWOA), which combines chaotic and multi-swarm strategies. Using several well-known medical diagnosis problems of breast cancer, diabetes, and erythemato-squamous, the proposed SVM model, termed CMWOAFS-SVM, was compared with multiple competitive SVM models based on other optimization algorithms including the original algorithm, particle swarm optimization, bacterial foraging optimization, and genetic algorithms. The experimental results demonstrate that CMWOAFS-SVM significantly outperformed all the other competitors in terms of classification performance and feature subset size. [Display omitted] •A multi-swarms with stratified mechanism is introduced to construct a multi-swarms WOA.•Chaos population initialization and self-adaption chaotic disturbance mechanism are introduced.•The proposed method has tackled the parameter optimization and feature selection.