Bibliographic record
Abstract
Abstract. The purpose of this research is to develop an approach for a Spatial Decision Support System (SDSS) that integrates Geographic Information Systems (GIS), Automated Machine Learning (AutoML), and Hyperparameter Optimization (HPO) to generate precision geo-interventions based on standardized geospatial data and user design constraints. The geo-intervention generation approach involves three steps: (1) Geo-binning, (2) AutoML, and (3) Prediction Optimization. Geo-binning is used to standardize geospatial data into regularized grids as inputs into AutoML models. Prediction optimization generates geo-interventions by applying user-design constraints and optimizing AutoML model output to find optimized input variables that form precise geo-interventions. An experiment in reducing road traffic collisions using infrastructural changes in Toronto, Ontario, Canada was done to evaluate the geo-intervention generation approach. The results of the experiment found that changing the number of schools, red light cameras, and transit shelters in high traffic areas could potentially halve the total number of traffic collisions according to a 80 by 80 geo-binned grid Auto-Sklearn model with a Mean Absolute Error (MAE) of 117.68. It was also found that user design constraints heavily affected the prediction optimization step as when the areas were altered to an alternative grid of cells with scarce infrastructure, the number of predicted collisions rose by 6127 collisions. Thus, limitations of this study included subjectivity in user design constraints, scalability, and interactivity. Future work involves improving modelling/optimization efficiency and developing an interactive interface for exploring generated precision geo-interventions.
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 | 0.004 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| 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".