A dynamic framework for tuning SVM hyper parameters based on Moth-Flame Optimization and knowledge-based-search

作者：

Highlights：

• Considered dynamic nature of data for real world problems.

• Proposed shift detection for shifting optimum.

• Proposed knowledge based search with MFO.

• Fast convergence rate to minimize execution time.

• Proposed framework is highly inclined towards accuracy of SVM.

摘要

•Considered dynamic nature of data for real world problems.•Proposed shift detection for shifting optimum.•Proposed knowledge based search with MFO.•Fast convergence rate to minimize execution time.•Proposed framework is highly inclined towards accuracy of SVM.

论文关键词：Support Vector Machine,Hyper-parameters,Model selection,Swarm Intelligence,Moth-Flame Optimization

论文评审过程：Received 4 April 2020, Revised 14 September 2020, Accepted 17 October 2020, Available online 2 November 2020, Version of Record 24 January 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114139