Investigating the Factors Affecting Speeding Violations in Jordan Using Phone Camera, Radar, and Machine Learning
DOI: 10.3389/fbuil.2022.917017
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study investigates the factors influencing speeding violations in Irbid, Jordan, aiming to identify high-risk areas and evaluate measurement techniques for traffic enforcement. Motivated by the high prevalence of traffic accidents in Jordan, where speeding is a primary cause of severe injuries and fatalities, the research seeks to determine specific driver, vehicle, road, and environmental variables that correlate with speed limit violations. The authors also address a gap in existing literature by integrating machine learning algorithms with field data collected via radar and phone cameras. The methodology involved analyzing 17,237 traffic accident records from the Jordan Traffic Institute spanning 2015 to 2019. The researchers employed two decision tree machine learning algorithms—Classification and Regression Tree (CART) and J48—using the WEKA software to predict speeding violations based on variables such as age, vehicle type, speed limit, day of the week, season, and weather conditions. To validate findings and assess measurement accuracy, the study identified seven speeding violation hot spots in Irbid. Field measurements were conducted in September 2021 using both a radar gun and a phone camera. For each site, 100 speed records were collected under clear, dry conditions. Video-based speeds were calculated by measuring the time vehicles took to pass defined distances, while radar provided direct speed readings. Statistical tests, including the Kolmogorov-Smirnov test and independent samples t-test, were used to compare the accuracy of the two measurement methods. The results indicated that age, vehicle type, speed limit, day of the week, season, accident year, accident time, license category, and light conditions significantly affect speeding violations. Specifically, drivers aged 26–35 and 36–45, passenger car users, and those driving during morning rush hours (7:00–8:59) exhibited higher violation rates. Speeding was also more prevalent in winter, on weekdays, and during daylight hours due to clear visibility. A speed limit of 40 km/h in residential areas was strongly associated with violations. The CART algorithm demonstrated slightly higher performance than J48, with an accuracy of 97.47% and a Kappa statistic of 0.949. Field measurements revealed that the 85th percentile speed at all seven hot spots was below the posted speed limits. When comparing measurement tools, the study found no significant statistical difference in accuracy between radar and video methods, though video measurements showed slightly higher mean speeds in some locations. The significance of this research lies in its comprehensive identification of risk factors for speeding in Jordan, providing actionable insights for traffic safety management. By pinpointing specific high-risk demographics, times, and locations, authorities can target enforcement efforts more effectively. Furthermore, the validation of phone cameras as a reliable alternative to radar guns offers a cost-effective solution for traffic monitoring and enforcement. The study underscores the importance of addressing behavioral factors, such as young drivers’ risk perception and morning rush hour pressures, alongside infrastructure adjustments like appropriate speed limit setting in residential zones.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-20 |
| archive | success | canonical_url | — | — | 1 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-20 |
| chunk | success | chunk | — | — | 1 | 2026-06-20 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-20 |
| promote | success | — | — | — | 1 | 2026-06-20 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-20 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: observational prevalence