Least squares support vector machine with self-organizing multiple kernel learning and sparsity

NEUROCOMPUTING

卷:331

Article

Liu, Chang¹  Tang, Lixin²  Liu, Jiyin³ 

[1] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Liaoning Engn Lab Data Analyt & Optimizat Smart I, Shenyang 110819, Liaoning, Peoples R China

[2] Northeastern Univ, Inst Ind & Syst Engn, Liaoning Key Lab Mfg Syst & Logist, Shenyang 110819, Liaoning, Peoples R China

[3] Loughborough Univ, Sch Business & Econ, Loughborough LE11 3TU, Leics, England

关键词: Least squares support vector machines;    Self-organizing multiple kernel learning;    Sparse selection;    Differential evolution;   

DOI  :  10.1016/j.neucom.2018.11.067

来源: Elsevier

【 摘 要 】

In recent years, least squares support vector machines (LSSVMs) with various kernel functions have been widely used in the field of machine learning. However, the selection of kernel functions is often ignored in practice. In this paper, an improved LSSVM method based on self-organizing multiple kernel learning is proposed for black-box problems. To strengthen the generalization ability of the LSSVM, some appropriate kernel functions are selected and the corresponding model parameters are optimized using a differential evolution algorithm based on an improved mutation strategy. Due to the large computation cost, a sparse selection strategy is developed to extract useful data and remove redundant data without loss of accuracy. To demonstrate the effectiveness of the proposed method, some benchmark problems from the UCI machine learning repository are tested. The results show that the proposed method performs better than other state-of-the-art methods. In addition, to verify the practicability of the proposed method, it is applied to a real-world converter steelmaking process. The results illustrate that the proposed model can precisely predict the molten steel quality and satisfy the actual production demand. (C) 2018 Elsevier B.V. All rights reserved.

【 授权许可】

Free