Chaotic simulated annealing multi-verse optimization enhanced kernel extreme learning machine for medical diagnosis. (May 2022)

• Record Type: Journal Article
• Authors: Liu, Jiacong; Wei, Jiahui; Heidari, Ali Asghar; Kuang, Fangjun; Zhang, Siyang; Gui, Wenyong; Chen, Huiling; Pan, Zhifang
• Is Part Of: Computers in biology and medicine. Volume 144(2022)
• Publication Date: 2022-05
• Subjects: Multi-verse optimization -- Swarm intelligence -- Global optimization -- Kernel extreme learning machine -- Medical diagnosis; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105356
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Classification models such as Multi-Verse Optimization (MVO) play a vital role in disease diagnosis. To improve the efficiency and accuracy of MVO, in this paper, the defects of MVO are mitigated and the improved MVO is combined with kernel extreme learning machine (KELM) for effective disease diagnosis. Although MVO obtains some relatively good results on some problems of interest, it suffers from slow convergence speed and local optima entrapment for some many-sided basins, especially multi-modal problems with high dimensions. To solve these shortcomings, in this study, a new chaotic simulated annealing overhaul of MVO (CSAMVO) is proposed. Based on MVO, two approaches are adopted to offer a relatively stable and efficient convergence speed. Specifically, a chaotic intensification mechanism (CIP) is applied to the optimal universe evaluation stage to increase the depth of the universe search. After obtaining relatively satisfactory results, the simulated annealing algorithm (SA) is employed to reinforce the capability of MVO to avoid local optima. To evaluate its performance, the proposed CSAMVO approach was compared with a wide range of classical algorithms on thirty-nine benchmark functions. The results show that the improved MVO outperforms the other algorithms in terms of solution quality and convergence speed. Furthermore, based on CSAMVO, a hybrid KELM model termed CSAMVO-KELM is established for disease diagnosis. To evaluate its effectiveness, the new hybrid system was compared with a multitude of competitive classifiers on two disease diagnosis problems. The results demonstrate that the proposed CSAMVO-assisted classifier can find solutions with better learning potential and higher predictive performance. Highlights: This study proposes a new chaotic simulated annealing overhaul of MVO (CSAMVO). A modal entitled CSAMVO-KELM is established based on CSAMVO. CSAMVO-KELM model is utilized to tackle disease diagnosis scenarios. CSAMVO-KELM can realize relatively higher predictive performance.