ADABase Dataset

Autonomous Driving Cognitive Load Assessment Database

multimodal, public dataset, cognitive load, affective sensing, machine learning, autonomous driving, multiple tasks, human computer interface

Physiological

Electrocardiography, Electromyography, Photoplethysmogram, Respiration, Skin Temperature, Eye Tracking

Behavioral

Facial Action Coding System Action Units, Eye Tracking

Subjective

NASA TLX questionnaires, OCEAN personality traits.

Performance

Hit Rate, False Positive Rate and Reaction Time

Scenarios

Well established physiological n-back test and novel application motivated k-drive test.

Public

Raw signal recordings (>2 hours each) of 30 subjects for academic purposes.

Fast & Easy Access

import pandas as pd

# Continuously recorded ECG during the nback test
data = pd.read_hdf(subject_file, "SIGNALS", mode="r")
data.loc[data["STUDY"] == 'nback', ["TS", "ECG_RAW_II"]].dropna()

# Reaction time of subject for level 1, n-back test.
data = pd.read_hdf(subject_file, "PERFORMANCE", mode="r")
data.loc[
    (data["PHASE"] == "nback") &
    (data["LEVEL"] == 1), "VISUAL REACTION TIME"
]

# Accessing available values for each table
pd.read_hdf(subject_file, "SIGNALS").columns

Open hierarchical data format v5, readable with all common programming languages, including python using pandas package.

Request Access to Dataset

Contact the authors and request access after accepting our End User License Agreement (EULA).

Send Mail

Abstract and Screenshots

Driver monitoring systems play an important role in lower to mid-level autonomous vehicles. Our work focuses on the detection of cognitive load as a component of driver-state estimation to improve traffic safety. By inducing single and dual-task workloads of increasing intensity on 51 subjects, while continuously measuring signals from multiple modalities, based on physiological measurements such as ECG, EDA, EMG, PPG, respiration rate, skin temperature and eye tracker data, as well as behavioral measurements such as action units extracted from facial videos, performance metrics like reaction time and subjective feedback using questionnaires, we create ADABase (Autonomous Driving Cognitive Load Assessment Database) More...

Cite our work: BibTex

  @article{oppeltADABaseMultimodalDataset2022,
    author = {Oppelt, Maximilian P. and Foltyn, Andreas and Deuschel, Jessica and Lang, Nadine R. and Holzer, Nina and Eskofier, Bjoern M. and Yang, Seung Hee},
    title = {{{ADABase}}: {{A Multimodal Dataset}} for {{Cognitive Load Estimation}}},
    date = {2022-12-28},
    journaltitle = {Sensors},
    volume = {23},
    number = {1},
    pages = {340},
    issn = {1424-8220},
    doi = {10.3390/s23010340},
    url = {https://www.mdpi.com/1424-8220/23/1/340},
  }

Funding

This work was supported by the Bavarian Ministry of Economic Affairs, Regional Development and Energy through the Center for Analytics-Data-Applications (ADA-Center) within the framework of “BAYERN DIGITAL II” (20-3410-2-9-8). The hardware infrastructure is partly funded by the Federal Ministry of Education and Research under the project reference numbers 16FMD01K, 16FMD02 and 16FMD03.

Legal

The USER is able to access ADABase after signing our End Users License Agreement (EULA), that can be requested by mail using adabase (at) iis.fraunhofer.de. The USER may not use the DATABASE for any nonacademic purpose. According to paragraph 44b section 3 UrhG (German Copyright Act) text and data mining for commercial purposes is prohibited. Nonacademic purposes include, but are not limited to: proving the efficiency of commercial systems, training or testing of commercial systems, selling data from the dataset, creating military applications, developing governmental systems used in public spaces. If parties are interested in acquiring the dataset for commercial usage or undisclosed parts of the dataset, do not hesitate to contact us.