@inproceedings{80a806bebf124026b1e4135aef980717,
title = "Data-driven modeling of modal parameters of long-span bridges under environmental and operational variation",
abstract = "This study develops the multivariate model of modal parameters under the high variability of structural responses and environmental conditions. The automated operational modal analysis procedure is implemented by synthesizing the algorithms of output-only system identification and density-based clustering algorithm. The Gaussian Process Regression is applied to accumulated modal estimates as well as corresponding environmental/operational conditions for examining the high degree of nonlinear variation in these monitoring data. The performance of the developed model is demonstrated for one-to-one regressions for multivariate structural health monitoring outputs in the presence of environmental and operational variation.",
keywords = "Gaussian process regression, Multivariate regression, Operational modal analysis, Structural health monitoring",
author = "Sunjoong Kim and Spencer, {Billie F.} and Kim, {Ho Kyung} and Kim, {Se Jin} and Doyun Hwang",
note = "Publisher Copyright: {\textcopyright} 2021 IABSE Conference, Seoul 2020: Risk Intelligence of Infrastructures - Report. All rights reserved.; IABSE Conference Seoul 2020: Risk Intelligence of Infrastructures ; Conference date: 09-11-2020 Through 10-11-2020",
year = "2021",
language = "English",
series = "IABSE Conference, Seoul 2020: Risk Intelligence of Infrastructures - Report",
publisher = "International Association for Bridge and Structural Engineering (IABSE)",
pages = "170--173",
booktitle = "IABSE Conference, Seoul 2020",
}