eDREAM Dataset - a multimodal dataset for driver cognitive load estimation

The eDREAM dataset was created for research on using advanced sensor and vision technologies to assess cognitive loads on drivers.

  • 37 participants completed three driving sessions on a mid-fidelity fix-based simulator, with a different level of cognitive load in each drive.
  • The experiments were conducted with special attention to minimize the perturbation from other uninterested conditions, which facilitated isolation of varying cognitive loads.
  • A comprehensive set of sensors was incorporated, including:
    • Wireless electroencephalogram (EEG) headband
    • Electrocardiography (ECG), Galvanic Skin Responses (GSR) sensors and a respiration band
    • Remote eye-tracker
    • Participant-facing video-racordings
    • Participant-facing color cameras (The non-identifiable portion of the dataset can be available for research purposes.)
  •

    How to use

    This dataset is available for research purposes. more details of the dataset are provided on the dataset description pages, and files could be downloaded from the download page after authorizations and End User License Agreement.

    If you are interested in using this dataset, please cite it as:

              Author = {Liu, Cheng Chen, He, Dengbo and Donmez,
              Birsen and Plataniotis, Konstantinos N},
              Title = {eDREAM Data Collection Report},
              Year  = {2016},


    Assessing influence of high cognitive load on vehicle driver's electroencephalography (EEG) signals:

    Statistical analysis of the dataset results was published in:

    For applications of advanced sensory and vision techniques in smart driver monitoring, please refer to the high-level review article:


    We'd like to thank all participants of this study.

    We'd also like to thank NSERC and our partners, Qualcomm Canada Inc., InteraXon Inc., and MEA Forensic Engineers & Scientists for their support.