Data mining the Kansas traffic-crash database : final report.
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study addresses the need for improved highway safety analysis by developing crash rate prediction models for Kansas road networks. The research was motivated by the significant human and economic costs of traffic crashes and the Kansas Department of Transportation’s (KDOT) lack of in-depth analysis of its historical crash database, which contains records dating back to 1990. The primary objective was to utilize Artificial Neural Network (ANN) techniques to mine this database, examining the complex interactions between highway geometrics, traffic characteristics, and human factors to predict crash rates and identify hidden correlations. The researchers analyzed data from six distinct road networks: rural expressways, rural two-lane roads, rural freeways, rural KTA (Kansas Turnpike Authority) roads, urban freeways, and urban expressways. They developed unique ANN models for each network to predict four specific crash rate categories: Total Crash Rate, Injury Crash Rate, Severe Injury Crash Rate, and Fatal Crash Rate. Input variables included geometric factors such as lane width, median width, and shoulder width, as well as traffic characteristics like Average Annual Daily Traffic (AADT), percentage of heavy vehicles, and speed. The study also employed sensitivity analysis to determine the impact of continuous and categorical variables on crash behavior. Additionally, the research investigated human factors by analyzing the relationships between crash rates, driver age, vehicle type, and seat belt compliance using data aggregation. The findings indicate that geometric variables and traffic characteristics significantly impact crash behavior, but the specific effects of these variables vary considerably across different road networks, making generalization difficult. Sensitivity analysis revealed that continuous variables exert different influences depending on the specific network type. Regarding human factors, the study found that drivers aged 18–20 had the highest involvement in crashes across all road networks. Passenger cars exhibited the highest crash involvement among vehicle types, while bus drivers demonstrated the highest seat belt compliance rates. The developed ANN models successfully captured these complex, non-linear relationships, providing a robust framework for predicting crash rates based on specific roadway conditions. The significance of this work lies in its demonstration of ANN as a viable tool for mining historical traffic crash data, serving as a starting point for future safety analysis. The models developed are intended for use by KDOT to evaluate roadway design features, assess the impacts of reconstruction projects, and inform future traffic planning operations. By providing reliable estimates of anticipated crashes, these tools can serve as early warning systems, allowing transportation agencies to implement targeted safety measures proactively. This research highlights the potential of advanced data mining techniques to extract actionable insights from large historical datasets, thereby enhancing the ability of transportation departments to reduce traffic-related crashes and improve overall highway safety.
Key finding
Driver age group 18-20 had the highest crash involvement across all road networks, while bus drivers showed the highest seat belt compliance.
Methodology
dataset
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. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- incidence prevalence
- crash typology
- urban rural setting
- comparative international
- demographic disparities
- fatality injury trends
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: crash risk outcomes, observational prevalence
- Methodological Resource: dataset resource