Samuel da Silva | Associate Professor, São Paulo State University (UNESP), Ilha Solteira, Brazil
December 6, 2023 | 11h00-12h00 | Room U.0.6 | https://videoconf-colibri.zoom.us/j/93285885760 | Lusófona University, Lisbon, Portugal
Abstract: The practical limitation of applying machine learning to structural health monitoring (SHM) is the availability of sufficient experimental data for training. However, obtaining an extensive training database can be expensive or complicated. Incomplete datasets can lead to overfitting, incorrect classification, or poorly generalized results. Various approaches have been proposed to overcome this limitation, including data augmentation techniques based on numerical models or data-driven methods. This paper presents a novel data-driven strategy for improving feature-SHM classification, utilizing manifold sampling with a Dirichlet distribution. The proposed approach respects the underlying manifold structure of the original datasets of the features. Two examples illustrate the method’s application: the Z-24 bridge dataset and a three-story building structure dataset from the Los Alamos National Laboratory. In both cases, the technique efficiently generates samples with minimal computational effort, facilitating data augmentation to enhance the training of unsupervised and/or supervised methods for SHM purposes.
Short Bio: Samuel da Silva is an Associate Professor in the Mechanical Engineering Department at São Paulo State University – UNESP (Ilha Solteira/Brazil) and Research Fellow from National Council for Scientific and Technological Development (CNPq/Brazil). He obtained a B.S.E. and M.S. in Mechanical Engineering from UNESP – Ilha Solteira (Brazil) in 2002 and 2005, respectively, where he was FAPESP Graduate Research Fellow. In 2008 he received his Ph.D. in Mechanical Engineering from the State University of Campinas (UNICAMP) with a Sandwich Doctorate scholarship at Université de Franche-Comté (Besançon, France) (2007). He was Visiting Researcher at Arts et Métiers (Paris, France) with a São Paulo Research Foundation (FAPESP) fellowship from 2019 – 2020. Currently, he serves on the editorial board of the Journal of the Brazilian Society of Mechanical Sciences and Engineering. He has supervised 10 complete Ph.D. thesis and published more than 70 peer-review journal papers. His research interests cover Structural Health Monitoring, System Identification, Signal Processing, Nonlinear Dynamics, and Applied Mechanics. Website: https://www.samueldasilva.org/.