Robust GMM least square twin K-class support vector machine for urban water pipe leak recognition

作者：

Highlights：

• A novel improved multi-class support vector machine algorithm was proposed for urban water pipe leak recognition.

• The proposed GLT-KSVC algorithm solved two classification drawbacks of the current LST-KSVC.

• The Gaussian mixture model (GMM) method was applied to address outlier issue in pipe leak recognition.

摘要

•A novel improved multi-class support vector machine algorithm was proposed for urban water pipe leak recognition.•The proposed GLT-KSVC algorithm solved two classification drawbacks of the current LST-KSVC.•The Gaussian mixture model (GMM) method was applied to address outlier issue in pipe leak recognition.

论文关键词：Leak recognition,Outliers,LST-KSVC,GMM,GLT-KSVC

论文评审过程：Received 26 May 2021, Revised 2 September 2021, Accepted 7 January 2022, Available online 12 January 2022, Version of Record 5 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116525