ETTC Ranges for Vehicle Conflicts at Freeway Diverging Areas in China

48 vehicle motion parameters and surrogate safety measures were extracted from 12 interchange diverging areas on two multilane freeways in China. The dataset, created by Feng Tang, contains longitudinal and lateral conflict labels at 30-second intervals based on Extended Time-to-Collision (ETTC). It was last updated on 2026-04-29.

Use Cases

• Training machine learning models like XGBoost for crash risk prediction based on surrogate safety measures.
• Analyzing spatiotemporal patterns of severe lateral and longitudinal conflicts based on 30-second interval labels.
• Interpreting key risk factor contributions for dangerous driving warning systems using the SHAP framework.
• Comparing conflict duration and crash risk between lateral and longitudinal interactions near exit ramps.

Strengths

• Includes 48 extracted vehicle motion parameters and surrogate safety measures.
• Data is derived from 12 specific interchange diverging areas on two multilane freeways.
• Conflict labels are provided at a high temporal resolution of 30-second intervals.
• The dataset is small (5.5 KB), facilitating quick inspection and download.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is limited to 12 specific interchange areas in China, which may affect generalizability.

Provenance

Source

figshare, author Feng Tang.

Collection Method

Data was gathered using image recognition technology to extract parameters from freeway interchange areas.

Freshness

Last updated 2026-04-29 17:54:57; freshness should be verified.

Geography

12 interchange diverging areas from two multilane freeways in China.