Expert evaluation system for pothole defect detection
Bibliographic record
Abstract
• This study introduces an unsupervised approach for assessing pothole severity using vibration data. • The methodology incorporates IoT-enabled accelerometers facilitating scalable pavement monitoring. • A detailed performance comparison with a traditional wavelet-based changepoint algorithm is conducted. • The proposed system is validated using a full-scale study detecting pavement anomalies under realistic traffic conditions. • The adaptability of the proposed method is verified experimentally across varying test scenarios. The rapid deterioration of transportation infrastructure, accelerated by extreme weather events and increasing traffic loads, poses significant challenges for roadway maintenance. Potholes, a common form of pavement distress, not only compromise road safety but also increase vehicle maintenance costs and disrupt economic productivity. To address this issue, this study presents a mobile Internet-of-Things (IoT)-based pavement monitoring system for the automated detection and evaluation of potholes. The proposed system can detect and estimate pothole size based on real-time vibration data collected from unmanned ground vehicles (UGVs) by combining IoT-enabled accelerometers and a novel unsupervised threshold-based methodology. This paper introduces a scalable and cost-efficient framework that integrates IoT data acquisition technology with advanced pavement monitoring algorithms, providing municipalities and infrastructure managers with an automated solution for identifying and prioritizing road repairs. The proposed system was validated through multiple field trials and a full-scale study, where it accurately identified potholes of varying sizes across different road conditions. The threshold-based proposed approach is compared with a wavelet-based changepoint detection algorithm to demonstrate its versatility in delivering reliable and robust results even in adverse environmental conditions. The proposed method is validated using nine potholes of varying sizes which are successfully identified and estimated without any user intervention.
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 | 0.013 |
| 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 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.022 | 0.008 |
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".