DP-GMM clustering-based ensemble learning prediction methodology for dam deformation considering spatiotemporal differentiation
作者：
Highlights：
• A clustering-based ensemble learning model for dam health monitoring is proposed.
• Combining DPC and GMMC to avoid the inaccurate spatiotemporal segmentation.
• Multi-output SVM and ELM are introduced to handle the correlation of outputs.
• Multi-output ensemble learning framework is developed for complex mapping learning.
• The proposed methodology shares the excellent performance in dam behavior forecast.
摘要
•A clustering-based ensemble learning model for dam health monitoring is proposed.•Combining DPC and GMMC to avoid the inaccurate spatiotemporal segmentation.•Multi-output SVM and ELM are introduced to handle the correlation of outputs.•Multi-output ensemble learning framework is developed for complex mapping learning.•The proposed methodology shares the excellent performance in dam behavior forecast.
论文关键词：Deformation prediction,Spatiotemporal differentiation,Multi-output ensemble learning,Spatiotemporal clustering,Synchronous optimization
论文评审过程：Received 1 November 2020, Revised 24 January 2021, Accepted 15 March 2021, Available online 20 March 2021, Version of Record 8 April 2021.
论文官网地址：https://doi.org/10.1016/j.knosys.2021.106964
