English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Monitoring bridge health using the vibrations of drive-by vehicles hasvarious benefits, such as low cost and no need for direct installation oron-site maintenance of equipment on the bridge. However, many such approachesrequire labeled data from every bridge, which is expensive and time-consuming,if not impossible, to obtain. This is further exacerbated by having multiplediagnostic tasks, such as damage quantification and localization. One way toaddress this issue is to directly apply the supervised model trained for onebridge to other bridges, although this may significantly reduce the accuracybecause of distribution mismatch between different bridges'data. To alleviatethese problems, we introduce a transfer learning framework usingdomain-adversarial training and multi-task learning to detect, localize andquantify damage. Specifically, we train a deep network in an adversarial way tolearn features that are 1) sensitive to damage and 2) invariant to differentbridges. In addition, to improve the error propagation from one task to thenext, our framework learns shared features for all the tasks using multi-tasklearning. We evaluate our framework using lab-scale experiments with twodifferent bridges. On average, our framework achieves 94%, 97% and 84% accuracyfor damage detection, localization and quantification, respectively. within onedamage severity level.

Knowledge transfer between bridges for drive-by monitoring using adversarial and multi-task learning