GUI-based hybrid ML model for predicting ultimate strength of FRP-confined UHPC with CTGAN-augmented data
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Fiber-reinforced polymer (FRP)-confined ultra-high-performance concrete (UHPC) is a promising form for advanced structural applications because of its superior mechanical performance and resilience. Meanwhile, consistent prediction models for the ultimate strength of FRP-confined UHPC stays limited, specifically due to the scarcity of sufficient experimental data. Hence, the current study proposes innovative machine learning (ML)-based framework that combines a conditional tabular generative adversarial network (CTGAN) with Optuna, a cutting-edge hyperparameter optimization algorithm, to address limitations of datasets and improve model generality. A processed experimental data consisting of 145 FRP-confined UHPC samples was assembled from the literature and utilized to train the model. Using the augmented dataset, a stacked hybrid ML model integrating multiple algorithms with ridge regression as the meta -learner was developed. The proposed model demonstrated superior predictive performance compared to individual ML models, achieving a correlation coefficient of 0.984 along with consistently low performance error metric. SHAP analysis shown that feature hierarchies between original and augmented datasets were strongly correlated, confirming that CTGAN preserved the input–output relationships. Furthermore, the leave-one-study-out validation demonstrated robust cross-study generalization, with CTGAN-generated data achieving error levels comparable to experimental datasets. Finally, a user-friendly graphical user interface (GUI) was developed for structural design applications.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it