Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Semi supervised identification of numerically simulated pile defects using graph label prppagation

Eftychios Protopapadakis, Stavroulakis Georgios, Marco Schauer, Anastasios Doulamis, Jens Böhrnsen, Sabine Langer

Full record


URI: http://purl.tuc.gr/dl/dias/A82474BC-856E-45FD-8ACA-2EDEBD214C59
Year 2015
Type of Item Conference Poster
License
Details
Bibliographic Citation E. Protopapadakis, M. Schauer, A. Doulamis, G. Stavroulakis, J. Böhrnsen, S.Langer,.(2015,Jul.).Semi supervised identification of numerically simulated pile defects using graph label prppagation .Presented at 8th GRACM International Congress on Computational Mechanics.[online]. Available:http://8gracm.mie.uth.gr/Papers/Session%20D3-C1/E.%20Protopapadakis.pdf
Appears in Collections

Summary

A graph-based detector is utilized for the identification of structural defects in piles. The approach utilize semi supervised learning assumptions, which allow the exploitation of the unlabeled data to produce accurate defect identifications. A coupled finite element and scaled boundary finite element method approach is used to simulate the pile and its surrounding soil. The proposed defect detection system provides information about the type and the placement of the defect(s), given the surface's oscillation patterns.

Services

Statistics