A scalable fuzzy support vector machine for fault detection in transportation systems

作者：

Highlights：

• Fuzzy support vector machine is used for fault detection in high speed train.

• A new KNN-based method is proposed for calculating fuzzy membership values.

• The new method is scalable for imbalanced big data.

• The computation burden is largely reduced in the experiment on a real dataset.

摘要

•Fuzzy support vector machine is used for fault detection in high speed train.•A new KNN-based method is proposed for calculating fuzzy membership values.•The new method is scalable for imbalanced big data.•The computation burden is largely reduced in the experiment on a real dataset.

论文关键词：Prognostics and health management,High-speed train,Fuzzy SVM,Fuzzy membership calculation,Imbalanced data

论文评审过程：Received 11 October 2017, Revised 7 February 2018, Accepted 8 February 2018, Available online 20 February 2018, Version of Record 19 March 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.02.017