moabb.datasets.BNCI2022_001#

class moabb.datasets.BNCI2022_001[source]#

BNCI 2022-001 EEG Correlates of Difficulty Level dataset.

Dataset summary

#Subj	13
#Chan	67
#Classes	4
#Trials / class	varies
Trials length	90 s
Freq	256 Hz
#Sessions	1
#Runs	1
Total_trials	varies

Participants

Population: normal or corrected-to-normal vision, no history of motor or neurological disease (one subject with history of vasovagal syncope)
Age: 22.6 years
Handedness: 12 right-handed, 1 left-handed

Equipment

Amplifier: Biosemi ActiveTwo
Electrodes: active
Montage: 10-10
Reference: Car

Preprocessing

Data state: downsampled raw
Bandpass filter: 1-40 Hz
Steps: downsampling from 2048 Hz to 256 Hz
Re-reference: car

Data Access

DOI: 10.1109/TAFFC.2021.3059688

Experimental Protocol

Paradigm: imagery
Feedback: none
Stimulus: avatar

Dataset from [1].

Dataset Description

This dataset contains EEG recordings from 13 subjects performing a simulated drone piloting task through waypoints at varying difficulty levels. The study aimed to decode the subjective perception of task difficulty from EEG signals to help optimize operator performance by automatically adjusting task difficulty.

Subjects controlled a simulated drone through circular waypoints using a flight joystick. The difficulty was modulated by the size of waypoints - smaller waypoints required more precise control and were perceived as more difficult. After each trajectory, subjects reported their perceived difficulty level.

Participants

13 healthy subjects (8 females, mean age 22.6 years, SD 1.04)
All had normal or corrected-to-normal vision
No history of motor or neurological disease
Location: EPFL, Geneva, Switzerland

Recording Details

Equipment: Biosemi ActiveTwo system
Channels: 64 EEG + 3 EOG = 67 total
Original sampling rate: 2048 Hz (downsampled to 256 Hz in public release)
Hardware trigger recorded as 8-bit signal
Baseline recording: 1-minute eye close/open

Experimental Procedure

Subjects sat in front of a monitor controlling a flight joystick with their right hand
Task: Pilot simulated drone through circular waypoints
32 trajectories per subject, each with 32 waypoints (~90 seconds each)
16 difficulty levels (waypoint sizes), normalized to each subject’s skill
Difficulty progression: levels 16->1->16 (decreasing then increasing)
After each trajectory, subjects reported:
- Numeric difficulty level (0-100)
- Categorical difficulty (easy/hard/extremely hard)

Event Codes

trajectory_start (1): Beginning of trajectory (countdown before drone moves)
waypoint_miss (16): Drone failed to pass through waypoint
waypoint_hit (48): Drone successfully passed through waypoint
trajectory_end (255): End of trajectory (3s after final waypoint)

Data Organization

1 session per subject (offline data only, online sessions not included)
Two file types per subject:
- Baseline: eye close/open recording
- Task (wpsize): main piloting task with difficulty variations

References

[1]

Jao, P.-K., Chavarriaga, R., & Millan, J. d. R. (2021). EEG Correlates of Difficulty Levels in Dynamical Transitions of Simulated Flying and Mapping Tasks. IEEE Transactions on Human-Machine Systems, 51(2), 99-108. https://doi.org/10.1109/THMS.2020.3038339

Notes

Added in version 1.3.0.

This dataset is designed for cognitive workload assessment and difficulty level detection. Unlike motor imagery datasets, the task involves actual motor control while the cognitive state (perceived difficulty) varies.

The public release contains only the first session (offline) data. Additional behavioral data and online sessions with closed-loop difficulty adaptation are not included. The paradigm “imagery” is used for compatibility, though the actual task involves motor execution with cognitive load variations.