Related Experiment Video
Updated: May 15, 2026
11:41
Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation
Published on: February 1, 2020
Evaluating the performance of network screening methods for detecting high collision concentration locations on
Oh Hoon Kwon1, Min Ju Park, Hwasoo Yeo
1Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 305-701, South Korea.
Accident; Analysis and Prevention
|December 19, 2012
Summary
The Continuous Risk Profile (CRP) method is most effective for identifying freeway high-collision sites, showing fewer false positives than Sliding Moving Window (SMW) and Peak Searching (PS) methods. Its performance remained consistent across different safety models.
Area of Science:
- Traffic Safety
- Transportation Engineering
- Statistical Analysis
Background:
- Identifying high-collision concentration locations (hot spots) is crucial for effective traffic safety interventions.
- Existing methods for site segmentation vary in their performance and reliability.
Purpose of the Study:
- To evaluate and compare the performance of three freeway site segmentation methods: Sliding Moving Window (SMW), Peak Searching (PS), and Continuous Risk Profile (CRP).
- To determine which method is most effective in accurately identifying high-collision locations for safety investigations.
Main Methods:
- Segmented freeway sites using SMW, PS, and CRP methods.
- Estimated excess expected average crash frequency using Empirical Bayes adjustment and two sets of Safety Performance Functions (SPFs).
- Compared prioritized site lists from each method against confirmed hot spots.
Main Results:
- Method performance varied significantly despite identical input requirements.
- The Continuous Risk Profile (CRP) method demonstrated the lowest false positive rate.
- Sliding Moving Window (SMW) and Peak Searching (PS) performance fluctuated with different SPFs, unlike CRP.
Conclusions:
- The CRP method offers a more reliable approach for identifying freeway high-collision sites compared to SMW and PS.
- The robustness of CRP to variations in Safety Performance Functions enhances its utility in traffic safety analysis.
