Discover datasets

The BCIAUT-P300 dataset comprises EEG recordings from 15 individuals with autism spectrum disorder (ASD) participating in a P300-based brain-computer interface (BCI) study focused on joint-attention training in a virtual environment. Data were collected across 7 sessions using 8 EEG channels sampled at 250 Hz, with visual stimuli presented as flashing objects. This multi-session, multi-subject benchmark dataset enables evaluation of P300 detection algorithms and BCI performance in the clinical ASD population.

Participants

15

Channels

8 (10-10)

Citations

67

HED

v8.4.0

Size

9.33 GB

Version

v1.0.2

Updated

Aug 18, 2026

This dataset contains 64-channel EEG recordings from 25 healthy human subjects performing a motor imagery brain-computer interface (BCI) task combined with overt spatial attention, across 5 sessions per subject. Participants imagined left- or right-hand movements while receiving continuous cursor feedback, enabling study of integrated motor imagery and spatial attention paradigms for BCI control. The dataset was converted to BIDS format using MOABB from source data originally collected at Carnegie Mellon University.

Participants

25

Channels

64 (10-10)

Citations

22

HED

v8.4.0

Size

184 GB

Version

v1.0.4

Updated

Aug 20, 2026

This dataset comprises EEG recordings from 15 healthy subjects performing a P300-based brain-computer interface task for door lock control. The experiment employed a visual oddball paradigm with 31-channel EEG acquisition at 500 Hz, generating event-related potentials in response to target and non-target stimuli presented on an LCD display. The dataset includes 50 training and 30 testing trials per subject and serves as a benchmark for P300-based BCI applications in home appliance control.

Participants

14

Channels

31 (10-10)

Citations

8

HED

v8.4.0

Size

1.24 GB

Version

v1.0.3

Updated

Aug 18, 2026

This dataset comprises EEG recordings from 15 healthy subjects performing an auditory brain-computer interface task based on the ASME (Auditory Stream segregation Multiclass ERP) paradigm. The study investigates two strategies for achieving four-class classification: ASME-4stream (four independent streams with single target stimuli) and ASME-2stream (two streams with dual target stimuli each). EEG data were recorded at 1000 Hz from 64 channels and analyzed using event-related potential methods and linear discriminant analysis classification, achieving accuracies of 83% and 86% respectively.

Participants

15

Channels

64 (10-10)

Citations

6

HED

v8.4.0

Size

23.5 GB

Version

v1.0.4

Updated

Aug 18, 2026

A multi-session EEG dataset acquired from 15 healthy participants performing resting state and graded cognitive tasks (MATB-II at three difficulty levels). The dataset comprises 62-channel EEG recordings at 500 Hz sampling rate designed for passive brain-computer interface applications and mental workload estimation in neuroergonomic contexts. Raw EEG data are provided with standardized event annotations using HED 8.4.0 schema and MOABB-compatible feature extraction pipelines (bandpower analysis and Riemannian covariance methods) for benchmarking purposes.

Participants

15

Citations

61

HED

v8.4.0

Size

1.22 GB

Version

v1.0.0

Updated

Jul 10, 2026

This dataset contains EEG recordings from a collaborative brain-computer interface (BCI) study using rapid serial visual presentation (RSVP) for target image detection. Fourteen healthy subjects, organized into seven pairs, performed synchronized RSVP tasks distinguishing human from non-human images, generating p300-like event-related potentials. The dataset is a BIDS-formatted derivative converted using the MOABB toolbox from the original data by Zheng et al. (2020).

Participants

14

Channels

62 (10-10)

Citations

27

HED

v8.4.0

Size

11.9 GB

Version

v1.0.3

Updated

Aug 21, 2026

A P300-based brain-computer interface dataset for home appliance control, comprising EEG recordings from 14 healthy subjects performing a visual oddball task with 31-channel recordings at 500 Hz sampling rate. The dataset includes 50 training and 30 testing blocks per subject, with target and non-target stimulus classifications presented via LCD display in an online BCI paradigm.

Participants

14

Channels

31 (10-10)

Citations

9

HED

v8.4.0

Size

644 MB

Version

v1.0.3

Updated

Aug 18, 2026

Participants

13

Citations

2

HED

v8.4.0

Size

2.82 GB

Version

v1.0.0

Updated

Jul 10, 2026

Participants

25

Citations

3

HED

v8.4.0

Size

54.4 MB

Version

v1.0.0

Updated

Jul 10, 2026

This derivative dataset presents an event-related potential (ERP) paradigm from the Mobile BCI dataset, comprising 24 healthy participants performing visual oddball tasks during various locomotion states (standing, walking, running). The dataset includes 73-channel EEG recordings sampled at 100 Hz with 5 sessions per subject, annotated with HED 8.4.0 event tags for target and non-target stimuli. This resource enables investigation of P300-based brain-computer interface performance in mobile and dynamic environments.

Participants

24

Channels

48 (10-10)

Citations

34

HED

v8.4.0

Size

8.08 GB

Version

v1.0.2

Updated

Aug 18, 2026