A new sampling strategy for SVM-based response surface for structural reliability analysis
- Submitting institution
-
The University of West London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 12052
- Type
- D - Journal article
- DOI
-
10.1016/j.probengmech.2015.04.001
- Title of journal
- Probabilistic Engineering Mechanics
- Article number
- -
- First page
- 1
- Volume
- 41
- Issue
- -
- ISSN
- 0266-8920
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
-
This paper has addressed an area of importance in engineering science with limited research and knowledge by adopting Support Vector Method. An excellent early example of machine learning and active learning approaches in structural reliability analysis. A novel sampling strategy applied on a second-order response surface based on the SVM was introduced. Extensive numerical experimental results validated each type of limit state scenarios considered. This research supported several major external funding including, “Resilient Artificial Intelligence System Engineering, Tsinghua-Berkeley Universities, £1.8m, (2019), and “A Data-Driven Optimization Approach to Improve the Resilience of the Singapore Mass Rapid Transit Network, £150k, (2018)”.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
