Data integration using deep learning and real-time locating system (RTLS) for automated construction progress monitoring and reporting
Bibliographic record
Abstract
The shift towards automated progress monitoring using new technologies for efficient delivery of construction projects has received significant attention. The application of vision-based techniques for object recognition and real-time locating system (RTLS) for object localization has been widely studied. However, a single technology cannot provide complete information needed to determine the status of tracked elements on a job site. This paper presents an integrated method for progress monitoring through recognition and localization of elements in construction sites. This method integrates data derived from a deep learning model and Ultra-wideband (UWB) system, and reports each element's ID, location, visual data and capture time. Such information is essential for project managers to assess progress on site. The method is validated in a mechanical room, a challenging environment for RTLS and object recognition models due to signal interferences and occlusions. The findings suggest further research on improving integrated methods for efficient progress reporting. • An integrated method for progress monitoring and reporting has been developed. • A deep learning model, and UWB system were used for the recognition and localization of components. • The method was evaluated in a mechanical room, which is a high multipath environment. • Results from the deep learning model and UWB system were reported for assessment of project status.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".