Discover datasets

The Munich Motor Imagery dataset comprises electroencephalographic recordings from 10 healthy subjects performing two-class motor imagery tasks (left and right hand) cued by visual arrow stimuli. The dataset includes 128-channel EEG data sampled at 500 Hz with preprocessed signals suitable for brain-computer interface research and benchmarking of spatial filtering and classification methods.

Participants

10

Channels

128 (other)

Citations

74

HED

v8.4.0

Size

5.49 GB

Version

v1.0.2

Updated

Aug 18, 2026

This EEG dataset comprises recordings from 9 individuals with CNS tissue damage (stroke and spinal cord injury) performing five mental imagery tasks: word association, mental subtraction, spatial navigation, and motor imagery of the right hand and feet. Data were collected across two sessions using 30-channel EEG at 256 Hz with visual cue-guided paradigm. The dataset includes preprocessed signals with artifact rejection and is intended for brain-computer interface research and motor imagery classification studies.

Participants

9

Channels

30 (10-10)

Citations

74

HED

v8.4.0

Size

2.74 GB

Version

v1.0.2

Updated

Aug 18, 2026

The BNCI2003_IVa Motor Imagery dataset comprises EEG recordings from 5 healthy subjects performing motor imagery tasks (right hand and feet movements) in response to visual cues. This preprocessed dataset, originally from BCI Competition III, contains 280 trials per subject recorded with 118 EEG channels at 100 Hz sampling rate. The dataset has been extensively used for benchmarking brain-computer interface classification algorithms, particularly for evaluating common spatial patterns and feature combination methods.

Participants

5

Channels

118 (10-05)

Citations

86

HED

v8.4.0

Size

735 MB

Version

v1.0.3

Updated

Aug 18, 2026

This dataset contains simultaneous scalp and ear-EEG recordings from 6 healthy right-handed adults performing a motor execution task involving left and right hand fist clenching, cued by visual arrow stimuli. Recordings were made at 1000 Hz using a 122-channel Neuroscan SynAmps2 system, yielding 1114 trials, and are intended for benchmarking motor task classification algorithms such as EEGNet. The dataset was converted to BIDS format using MOABB and originates from a study investigating the utility of in-ear EEG sensing for motor task classification.

Participants

6

Channels

122 (10-05)

Citations

12

HED

v8.4.0

Size

18.4 GB

Version

v1.0.3

Updated

Aug 20, 2026

This dataset comprises EEG recordings from 9 healthy subjects performing two-class motor imagery tasks (left vs. right hand movements) as part of BCI Competition IV Dataset 2b. Data were collected across five sessions per subject: two screening sessions without feedback and three feedback sessions with visual smiley feedback. The dataset includes 3 bipolar EEG channels (C3, Cz, C4) and 3 EOG channels sampled at 250 Hz, providing a benchmark resource for motor imagery-based brain-computer interface research.

Participants

1

Channels

3 (10-20)

Citations

83

HED

v8.4.0

Size

478 MB

Version

v1.0.2

Updated

Aug 18, 2026

A preprocessed EEG dataset comprising motor imagery recordings from 14 healthy participants performing imagined right-hand tapping, left-hand tapping, and rest tasks. The dataset contains 1,665 trials acquired at 1024 Hz using a 19-channel montage with standard 10-20 electrode placement. Data have been preprocessed with ICA artifact removal and frequency filtering, and include annotations for motor imagery classification and brain-computer interface applications.

Participants

14

Channels

19 (10-20)

Citations

9

HED

v8.4.0

Size

1.23 GB

Version

v1.0.2

Updated

Aug 18, 2026

A two-class motor imagery EEG dataset comprising 12 healthy, right-handed naive subjects performing sustained kinesthetic imagery of right-hand palmar grip versus bilateral feet plantar extension. The dataset includes 2 sessions per subject with 200 trials total (100 per class), recorded at 512 Hz from 13 EEG channels using g.tec hardware with visual and auditory feedback. Data were preprocessed with bandpass filtering (0.5-100 Hz) and notch filtering at 50 Hz, achieving 80% classification accuracy with LDA and Common Spatial Patterns features.

Participants

12

Channels

13 (10-10)

Citations

95

HED

v8.4.0

Size

2.83 GB

Version

v1.0.2

Updated

Aug 18, 2026

The BNCI 2014-001 Motor Imagery dataset is a widely-used benchmark for brain-computer interface research, comprising EEG recordings from 9 healthy subjects performing four-class motor imagery tasks (left hand, right hand, feet, and tongue). Each subject completed two sessions with 6 runs per session, yielding 200 training and 240 test trials. The dataset features 22 EEG channels plus 3 EOG channels (25 total) sampled at 250 Hz with minimal preprocessing (bandpass filtering 0.05-200 Hz), making it a standard resource for evaluating multi-class motor imagery classification algorithms and cross-session transfer learning approaches.

Participants

9

Channels

22 (10-10)

Citations

90

HED

v8.4.0

Size

1.38 GB

Version

v1.0.2

Updated

Aug 18, 2026

Motor imagery EEG dataset from 8 healthy subjects performing cue-based motor imagination tasks (right hand, feet, rest). Recorded at 512 Hz with 16 electrodes using g.tec g.USBamp amplifier. Dataset comprises 60 trials (20 per class, 3 seconds each) and was developed to validate robust asynchronous EEG-based brain-computer interface control. Data are preprocessed and re-referenced to earlobe.

Participants

8

Channels

16 (10-20)

HED

v8.4.0

Size

232 MB

Version

v1.0.2

Updated

Aug 18, 2026

A classical motor imagery EEG dataset comprising recordings from 7 healthy subjects performing left hand, right hand, and passive rest tasks. The dataset contains 19-channel EEG data sampled at 200 Hz with visual arrow cues guiding motor imagery tasks. This benchmark dataset is designed for evaluating brain-computer interface algorithms and motor imagery classification methods.

Participants

7

Channels

19 (10-20)

Citations

81

HED

v8.4.0

Size

1.20 GB

Version

v1.0.2

Updated

Aug 18, 2026