Ensemble learning for decision making in sustainable infrastructure
Bibliographic record
Abstract
Inferences about the prospective state of natural and man-made systems play a major role in designing better infrastructure and assessing the resiliency of current ones. The rapid change of such systems' responses prompts the urgent need to re-evaluate our understanding of the evolution of such systems. New predictive analytics are, hence, important for all energy, water and earth aspects of sustainable infrastructure. Ensemble learning, a branch of artificial intelligence, ushers innovative modeling approaches which are recent advancements in machine learning. According to a predefined ensemble architecture, a number of machine learners are generated and their inferences are integrated to produce stable and improved generalization ability. In order to advance the utilization of ensemble learning in sustainable infrastructure applications, along with developing novel ensemble frameworks, an interdisciplinary research approach is essential. To this extent, this dissertation deals with the development of generalized ensemble learning frameworks, inspired from a wide range of recent engineering problems in energy, water and earth. The results from a comprehensive ensemble analysis approach for the problem of seismic-induced liquefaction prediction emphasizes on the importance of the diversity-in-learning concept, which facilitates the development of a novel ensemble framework to exploit the diversity concept and tackle the requirements of the decentralized and disaggregated energy forecasting problems. The latter is a crucial research endeavor to develop stable ensemble-based regression models for time series forecasting, in general, and helps in innovating a new class of hybrid ensemble learning frameworks which are used in the design of flood detection systems.
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 | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".