Driving Dataset

1. Dataset Release

For academic purposes, we are happy to release our driving dataset. If you use our dataset for your experiment, please cite our paper.

Driving time : about 23 hours

Driving length : about 46km (round-trip)

Driving path : between Korea University and SANGAM World Cup Stadium

# of Driver : 10 (A to J classes in the dataset and our paper.)


  • You can find more detailed description for each field in this paper (Martinelli, Fabio, et al. "Human behavior characterization for driving style recognition in vehicle system." Computers & Electrical Engineering 83 (2020): 102504. https://doi.org/10.1016/j.compeleceng.2017.12.050 ). See the Table 1.

  • This paper cited our dataset, and provide more information than our original dataset. ;-)


2. Applicable Area

  • User (driver) classification based on driving pattern analysis

  • Personalization service (combined with infotainment service based on the classification result)

  • Auto theft detection


3. Publication

Byung Il Kwak, Jiyoung Woo and Huy Kang Kim, "Know Your Master: Driver Profiling-based Anti-theft Method", PST (Privacy, Security and Trust) 2016


4. Acknowledgement

This dataset is used for the the AI/ML based driver classification challenge track in '2018 Information Security R&D dataset challenge' in South Korea.

You can find additional resources and tutorials (written in Korean) in the above URLs.

Contact : Byung Il Kwak (kwacka12@korea.ac.kr ) or Huy Kang Kim (cenda@korea.ac.kr)