Related Experiment Video
Updated: Nov 15, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
Published on: December 18, 2020
A data mining approach to deriving safety policy implications for taxi drivers
Jiwon Park1, Seolyoung Lee2, Cheol Oh3
1Department of Smart City Engineering, Hanyang University at Ansan, 55 Hanyangdaehak-ro, Sangnok-gu, Ansan-city, Gyeonggi-do 15588, Republic of Korea.
Taxi driver characteristics significantly impact traffic safety, with higher crash rates than other vehicles. This study identifies high-risk drivers and proposes policies to improve taxi safety and driver well-being.
Area of Science:
- Transportation Science
- Occupational Health
- Data Mining
Background:
- Taxi crashes occur more frequently than with other vehicle types, highlighting significant traffic safety concerns.
- Understanding the intrinsic characteristics of taxi drivers is crucial for developing effective safety policies.
Purpose of the Study:
- To analyze the intrinsic characteristics of taxi drivers and their relationship to traffic accidents.
- To derive policy implications for enhancing taxi traffic safety and improving driver welfare.
Main Methods:
- A questionnaire survey collected data from 781 corporate taxi drivers in Korea.
- Two-stage data mining, including random forest, classified drivers into four types based on working conditions and welfare.
Main Results:
- Four driver types were identified: unspecified normal, work-life balanced, overstressed, and work-oriented.
- Factors contributing to high-risk taxi drivers were prioritized for policy development.
Conclusions:
- Policy recommendations include new measures (elderly driver evaluation, mental health programs), improvements (wage system, rest facilities), and elimination of negative factors (overtime restrictions).
- Implementing these policies is expected to reduce taxi accidents and enhance driver quality of life.
Related Concept Videos
Introduction to Test of Independence
The test statistic for a test of independence is similar to that of a goodness-of-fit test:
Hypothesis Test for Test of Independence
H0: The two variables (factors)...
Determination of Expected Frequency
The Availability Heuristic
Survey Safety
Pharmacovigilance
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...

