Deep learning has ushered in many breakthroughs in vision‐based detection via convolutional neural networks (CNNs), but the vibration‐based structural damage detection by CNN remains being refined. Thus, this study proposes a simple one‐dimensional CNN that detects tiny local structural stiffness and mass changes, and validates the proposed CNN on actual structures. Three independent acceleration databases are established based on a T‐shaped steel beam, a short steel girder bridge (in test field), and a long steel girder bridge (in service). The raw acceleration data are not pre‐processed and are directly used as the training and validation data. The well‐trained CNN almost perfectly identifies the locations of small local changes in the structural mass and stiffness, demonstrating the high sensitivity of the proposed simple CNN to tiny structural state changes in actual structures. The convolutional kernels and outputs of the convolutional and max pooling layers are visualized and discussed as well.
Background
Patients with inflammatory bowel disease (IBD) on anti-tumor necrosis factor alpha (TNF) agents may have lower immune response to the influenza vaccine. We aimed to evaluate the immunogenicity of the high dose (HD) vs standard dose (SD) influenza vaccine in patients with IBD on anti-TNF monotherapy.
Methods
We performed a randomized clinical trial at a single academic center evaluating the immunogenicity of the HD vs SD influenza vaccine in patients with IBD on anti-TNF monotherapy. Influenza antibody concentration was measured at immunization, at 2 to 4 weeks postimmunization, and at 6 months.
Results
Sixty-nine patients with IBD were recruited into the study, 40 on anti-TNF monotherapy, and 19 on vedolizumab, along with 20 healthy controls (HC). Patients with IBD receiving the HD influenza vaccine had significantly higher H3N2 postimmunization antibodies compared with those who received the SD influenza vaccine (160 [interquartile range 80 to 320] vs 80 [interquartile range 40 to 160]; P = 0.003). The H1N1 postimmunization levels were not significantly higher in the HD influenza vaccine (320 [interquartile range 150 to 320] vs 160 [interquartile range 80 to 320]; P = 0.18). Patients with IBD receiving the HD influenza vaccine and those on vedolizumab who received SD had equivalent antibody concentrations to HC (H1N1 P = 0.85; H3N2 P = 0.23; B/Victoria P = 0.20 and H1N1 P = 0.46; H3N2 P = 0.21; B/Victoria P = 1.00, respectively).
Conclusions
Patients with IBD on anti-TNF monotherapy receiving the HD influenza vaccine had significantly higher postimmunization antibody levels compared with SD vaccine. Clinicaltrials.gov (#NCT02461758).
This article presents a method that enables a finite element (FE) model to remesh itself for updating the geometric changes caused by structural damages, using computer vision (CV) techniques and geometric analyses. Currently, there is no mature automatic approach to utilize the information of structural damage detection (SDD) for structural state awareness. Thus, the purpose of this study is to automate the pipeline from the accomplishment of SDD to numerical analyses for fast structural capacity evaluation. CV techniques are used to determine the shapes and dimensions of both structural components and damages. Geometric analyses are used to develop the algorithms for automatically deleting, generating, and splitting the elements of FE models for updating the geometric changes. Experiments are performed on a plate and a C-shaped steel crossbeam of a bridge to demonstrate the effectiveness of the proposed method and algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.