Smart Rehabilitation-Planning Framework for Sustainable Infrastructure: Roofing Application
Bibliographic record
Abstract
Aging infrastructure assets, including buildings, require efficient rehabilitation to sustain services. However, current rehabilitation planning is a complex process that is challenged by strict budgets and the difficulty of identifying and delivering the assets that are most worthy of rehabilitation. Existing methods struggle not only with collecting inspection data but also with how to use these data to allocate the limited rehabilitation funds efficiently across the asset portfolio. This paper introduces a smart infrastructure rehabilitation framework that integrates inspection, fund allocation, and scheduling phases. Focusing on roofing elements, the proposed framework uses four novel components: (1) asset image analysis to quantify the size of sustained damage; (2) data-mining to further analyze the asset condition; (3) clustering and optimization to shortlist the assets that are most worthy of rehabilitation under a strict budget; and (4) repetitive scheduling to generate timely delivery plans for the budgeted rehabilitation works. The model was applied to the Toronto District School Board asset portfolio (300+ schools), and the model identified the buildings in most need of rehabilitation given a strict budget ($2.3 million) and offer a schedule for the efficient delivery of the required rehabilitation work within a 45-day period of the school’s summer break. Although this paper focuses on built-up building roofs, the framework is scalable to other types of assets.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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".