Prognosticating fabric-reinforced cementitious matrix-to-masonry bond and failure mechanisms using novel tabular variational autoencoder-augmented probabilistic model
Bibliographic record
Abstract
Fabric-reinforced cementitious matrix (FRCM) composite strengthening has emerged as an environmentally friendly and less invasive solution, and entails material compatibility with masonry substrates, and hence emerges as the sustainable solution for structural restoration. But the performance of the FRCM system primarily depends on the bond behaviour between the masonry and composite interface, which governs stress transfer and failure mode. However, the available experimental datasets lack diversity, especially with respect to categorical characteristics, limiting predictive capability and extrapolation potential of data-driven models. Therefore, in this study, a tabular variational autoencoder model was implemented to synthetically augment the experimental database to capture a higher range of input variability. Using this enriched dataset, probabilistic modelling techniques have been utilized, including Gaussian process, Bayesian neural network, and natural gradient boosting (NGB) in predicting critical FRCM-to-masonry bond behaviour that includes bond strength, slip, and respective failure modes. Among these developed probabilistic models, the NGB model performed both better in terms of accuracy as well as uncertainty quantification and gave interpretable results on the importance of features. Mean absolute percentage error value of the testing set of the NGB model using the synthetic dataset approach was 22.72% and 23.83% for bond strength and slip, respectively. For failure modes, the accuracy of the NGB model for the testing set was 84% with the synthetic dataset. The proposed hybrid method enhances predictability and aids in formulating more precise and uncertainty-based design strategies for the sustainable rehabilitation of deteriorated masonry infrastructure.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".