Related Experiment Video
Updated: Jun 28, 2026
07:15
Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
Published on: December 18, 2020
DriE-Cog dataset: A multimodal physiological-behavioural dataset for intelligent driving emergency response
Hongqiang Zhang1, Bing He1, Qiaosong Hei1
1Advanced interdisciplinary institute of Satellite Applications, State Key Laboratory of earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing, 100875, China.
Scientific Data
|June 25, 2026
Summary
This study introduces DriE-Cog, a new multimodal dataset for intelligent driving emergency response. It enhances driver safety systems by providing comprehensive physiological, cognitive, and behavioral data.
Area of Science:
- Intelligent Transportation Systems
- Human-Computer Interaction
- Cognitive Science
Background:
- Existing datasets for intelligent emergency response driving are insufficient for developing robust safety systems.
- A need exists for comprehensive data integrating physiological, cognitive, and behavioral aspects of emergency driving.
Purpose of the Study:
- To introduce DriE-Cog, a novel multimodal dataset for intelligent emergency response driving.
- To address the limitations in quantity and quality of current driving safety datasets.
Main Methods:
- Collected multimodal data from 51 participants across 4 driving scenarios with 12 emergency events each.
- Integrated data from eye tracking (ET), electroencephalography (EEG), photoplethysmography (PPG), galvanic skin response (GSR), and driving behavior.
- Validated the dataset through completeness checks, single-modal feature analysis, and multimodal classification performance evaluation.
Main Results:
- DriE-Cog comprises a rich collection of physiological, cognitive, and behavioral data for emergency driving scenarios.
- Dataset validation confirmed its completeness and the utility of multimodal data for classification tasks.
- Analysis revealed significant differences in single-modal features across driving events.
Conclusions:
- DriE-Cog offers a reliable foundation for advanced research in intelligent driving emergency response.
- The dataset supports the development of improved driver safety performance and operational stability.
- This resource facilitates deeper understanding and mitigation of risks in critical driving situations.
