EEGdash›NeMAR›NM000207

Iss. 207 · 15 subjects · 180 recordings · CC0-1.0

Dataset Brief · Kojima et al. 2024 (Dataset B) — Four-class ASME BCI

NM000207: eeg dataset, 15 subjects#

Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing

Citation: Simon Kojima, Shin’ichiro Kanoh (2024). Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing.

15-participant EEG dataset — Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing.

Data & curation Simon Kojima · Shin'ichiro Kanoh
Year 2024 · Distributed via NeMAR
Funding JSPS KAKENHI (Grant Number JP23K11811 to Shin'ichiro Kanoh)

EEG · 64 ch1000 HzBIDS 1.9.0Task · p300HealthyAuditoryAttention

Layer 01Study

What was asked

Hypothesis, independent & dependent variables, paradigm, cohort, and the editorial caveats around what the recordings can and cannot answer.

Layer 02Signal · BIDS

What was recorded

Sidecars, channels & electrodes, coordinate system, event semantics, and quality stats from the NEMAR pipeline when available.

Layer 03Training · ML

What you can train on

Recommended access modes — MNE Raw, braindecode windows, PyTorch DataLoader — plus the targets the metadata makes addressable.

§ 01Access · Get started

Quickstart#

Get Started

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000207

dataset = NM000207(cache_dir="./data")
# Get the raw object of the first recording
raw = dataset.datasets[0].raw
print(raw.info)

Query & Filter

Filter by subject

dataset = NM000207(cache_dir="./data", subject="01")

Advanced query

dataset = NM000207(
    cache_dir="./data",
    query={"subject": {"$in": ["01", "02"]}},
)

Iterate recordings

for rec in dataset:
    print(rec.subject, rec.raw.info['sfreq'])

Cite This Dataset

If you use this dataset in your research, please cite the original authors.

BibTeX

@dataset{nm000207,
  title = {Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing},
  author = {Simon Kojima and Shin'ichiro Kanoh},
}

§ 02Study · The README

About This Dataset#

Class for Kojima2024B dataset management. P300 dataset.

Schema: HED 8.4.0 | Browse: https://www.hedtags.org/hed-schema-browser

Class for Kojima2024B dataset management. P300 dataset

Target

├─ Sensory-event
├─ Experimental-stimulus

View full README

Class for Kojima2024B dataset management. P300 dataset

Target

     ├─ Sensory-event
     ├─ Experimental-stimulus
     ├─ Visual-presentation
     └─ Target

NonTarget

├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Non-target

Paradigm-Specific Parameters

Detected paradigm: p300
Number of targets: 4
Number of repetitions: 15
Stimulus onset asynchrony: {‘ASME-4stream_overall’: 150.0, ‘ASME-2stream_overall’: 300.0, ‘within_stream’: 600.0} ms

Data Structure

Trials: {‘ASME-4stream’: ‘600 stimuli per trial (4 trials per run, 6 runs)’, ‘ASME-2stream’: ‘300 stimuli per trial (4 trials per run, 6 runs)’}
Blocks per session: 12
Block duration: 90.0 s
Trials context: 12 runs alternating between ASME-4stream and ASME-2stream, 4 trials per run

Preprocessing

Data state: raw
Preprocessing applied: False

Signal Processing

Classifiers: Linear Discriminant Analysis (LDA), shrinkage-LDA
Feature extraction: mean amplitudes in 10 intervals (0.1s non-overlapping, 0-1.0s)
Frequency bands: analyzed=[0.1, 8.0] Hz

Cross-Validation

Method: 3-fold chronological cross-validation (BCI simulation); 4-fold chronological cross-validation (binary classification)
Evaluation type: offline simulation

Performance (Original Study)

Asme-4Stream Accuracy: 0.83
Asme-2Stream Accuracy: 0.86

BCI Application

Applications: communication
Environment: laboratory
Online feedback: False

Tags

Pathology: Healthy
Modality: auditory
Type: ERP, P300

Documentation

Description: Four-class ASME BCI investigation comparing two strategies for multiclassing: ASME-4stream (four streams with single target stimulus each) vs ASME-2stream (two streams with two target stimuli each)
DOI: 10.3389/fnhum.2024.1461960
Associated paper DOI: 10.3389/fnhum.2024.1461960
License: CC0-1.0
Investigators: Simon Kojima, Shin’ichiro Kanoh
Senior author: Shin’ichiro Kanoh
Contact: simon.kojima@ieee.org
Institution: Shibaura Institute of Technology
Department: Graduate School of Engineering and Science (Simon Kojima); College of Engineering (Shin’ichiro Kanoh)
Address: Tokyo, Japan
Country: JP
Repository: Harvard dataverse
Data URL: https://doi.org/10.7910/DVN/1UJDV6
Publication year: 2024
Funding: JSPS KAKENHI (Grant Number JP23K11811 to Shin’ichiro Kanoh)
Ethics approval: Review Board on Bioengineering Research Ethics of the Shibaura Institute of Technology
Keywords: brain-computer interface, electroencephalogram, event-related potential, auditory scene analysis, stream segregation, machine learning, NASA-TLX

Abstract

The ASME (Auditory Stream segregation Multiclass ERP) paradigm is used for an auditory brain-computer interface (BCI). Two approaches for achieving four-class ASME were investigated: ASME-4stream (four streams with a single target stimulus each) and ASME-2stream (two streams with two target stimuli each). Fifteen healthy subjects participated. ERPs were analyzed, and binary classification and BCI simulation were conducted offline using linear discriminant analysis. Average accuracies were 0.83 (ASME-4stream) and 0.86 (ASME-2stream). The ASME-2stream paradigm showed shorter latency and larger amplitude of P300, higher binary classification accuracy, and smaller workload. Both paradigms achieved sufficiently high accuracy (over 80%) for practical auditory BCI.

Methodology

Subjects performed 12 runs alternating between ASME-4stream and ASME-2stream paradigms. Each run contained 4 trials with ~90s duration. ASME-4stream presented 4 streams (SOA=0.15s, 600 stimuli/trial, ratio 9:1 standard:deviant). ASME-2stream presented 2 streams with 2 deviant stimuli each (SOA=0.3s, 300 stimuli/trial, ratio 8:1:1). EEG recorded at 1000 Hz from 64 channels. EOG artifacts removed using ICA on 15 PCs. Data filtered (1-40 Hz for ERP, 0.1-8 Hz for classification), epoched (-0.1 to 1.2s), downsampled to 250 Hz. Classification used shrinkage-LDA with mean amplitudes from 10 intervals (0-1.0s) as features. Performance evaluated using 4-fold chronological cross-validation. Usability assessed via NASA-TLX questionnaire.

References

Kojima, S. (2024). Replication Data for: Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing. Harvard Dataverse, V1. DOI: https://doi.org/10.7910/DVN/1UJDV6 Kojima, S. & Kanoh, S. (2024). Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing. Frontiers in Human Neuroscience 18:1461960. DOI: https://doi.org/10.3389/fnhum.2024.1461960 Appelhoff, S., Sanderson, M., Brooks, T., Vliet, M., Quentin, R., Holdgraf, C., Chaumon, M., Mikulan, E., Tavabi, K., Hochenberger, R., Welke, D., Brunner, C., Rockhill, A., Larson, E., Gramfort, A. and Jas, M. (2019). MNE-BIDS: Organizing electrophysiological data into the BIDS format and facilitating their analysis. Journal of Open Source Software 4: (1896). https://doi.org/10.21105/joss.01896 Pernet, C. R., Appelhoff, S., Gorgolewski, K. J., Flandin, G., Phillips, C., Delorme, A., Oostenveld, R. (2019). EEG-BIDS, an extension to the brain imaging data structure for electroencephalography. Scientific Data, 6, 103. https://doi.org/10.1038/s41597-019-0104-8 Generated by MOABB 1.5.0 (Mother of All BCI Benchmarks) NeuroTechX/moabb

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Age distribution by gender (n=15, range 23–23 yr, mean 22.0 yr)

20

Other · 15

Channel counts: 64 ch (n=180 recordings)

Sampling frequencies: 1000.0 Hz (n=180 recordings)

Total recording duration: 21 h 37 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 64 ch · EEG · 1000 Hz · 15 subjects, 180 recordings

Live trace viewer — sub-13 · ses-0 · task-p300 · run-24

Showing one representative recording out of 15 subjects and 180 recordings in this dataset. Browse the full set on OpenNeuro; drop any other _eeg.{set,edf,bdf,vhdr} file onto the viewer (or pass ?eeg=<url>) to inspect it.

Electrode layout — EEG · 64 sensors — 64 channels

NEMAR Processing Statistics#

The plots below are generated by NEMAR’s automated EEG pipeline. The histogram shows pipeline success for data cleaning and ICA decomposition, the percentage of data frames and EEG channels retained after artefact removal, line noise per channel (RMS, dB), and the age/gender distribution of participants.

HED event descriptors word cloud

§ 05Manifest · BIDS tree

Manifest#

File Explorer#

Browse the BIDS file structure of this dataset. Records are fetched on demand from the EEGDash catalog the first time you open the explorer.

Recordings—

Files—

Subjects—

Modalities—

Click to load file structure…

§ 06API · Programmatic access

API Reference#

Signature

eegdash.dataset

class

eegdash.dataset.NM000207(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)Kojima2024B_P300

Canonical—

Importable asNM000207 · Kojima2024B_P300

Sourceeegdash/dataset/registry.py · [source ↗]

class eegdash.dataset.NM000207(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing

Study:: nm000207 (NeMAR)
Author (year):: Kojima2024B_P300
Canonical:: —

Also importable as: NM000207, Kojima2024B_P300.

Modality: eeg; Experiment type: Attention; Subject type: Healthy. Subjects: 15; recordings: 180; tasks: 1.

Parameters:

cache_dir (str | Path) – Directory where data are cached locally.
query (dict | None) – Additional MongoDB-style filters to AND with the dataset selection. Must not contain the key dataset.
s3_bucket (str | None) – Base S3 bucket used to locate the data.
**kwargs (dict) – Additional keyword arguments forwarded to EEGDashDataset.

data_dir#

Local dataset cache directory (cache_dir / dataset_id).

Type:: Path

query#

Merged query with the dataset filter applied.

Type:: dict

records#

Metadata records used to build the dataset, if pre-fetched.

Type:: list[dict] | None

Notes

Each item is a recording; recording-level metadata are available via dataset.description. query supports MongoDB-style filters on fields in ALLOWED_QUERY_FIELDS and is combined with the dataset filter. Dataset-specific caveats are not provided in the summary metadata.

References

OpenNeuro dataset: https://openneuro.org/datasets/nm000207 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000207

Examples

>>> from eegdash.dataset import NM000207
>>> dataset = NM000207(cache_dir="./data")
>>> recording = dataset[0]
>>> raw = recording.load()

__init__(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

save(path: str, overwrite: bool = False, offset: int = 0)[source]#

Save datasets to files by creating one subdirectory for each dataset:

path/
    0/
        0-raw.fif | 0-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)
    1/
        1-raw.fif | 1-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)

Parameters:

path (str) –

Directory in which subdirectories are created to store
-raw.fif | -epo.fif and .json files to.
overwrite (bool) – Whether to delete old subdirectories that will be saved to in this call.
offset (int) – If provided, the integer is added to the id of the dataset in the concat. This is useful in the setting of very large datasets, where one dataset has to be processed and saved at a time to account for its original position.

Access modesMNE → braindecode → PyTorch → ML

.rawMNE Raw object — standard tools (filter, epoch, ICA, plot_psd).mne

BaseConcatDatasetEach record is a lazy BaseDataset from braindecode — windowed via create_windows_from_events.braindecode

DataLoaderWraps the windowed dataset into a PyTorch DataLoader; supports parallel workers and on-the-fly augmentations.pytorch

Zarr cacheOptional braindecode Zarr mirror for fast resume; persisted to cache_dir.zarr

Hugging FaceNo per-dataset mirror published yet — browse the EEGDash org listing for sibling datasets. See the datasets loader API.huggingface

Croissant 1.0Machine-readable JSON-LD descriptor — NM000207.croissant.json (MLCommons schema, ingestible by PyTorch / TensorFlow / JAX).mlcommons

Examples using EEGDashcurated · start here

Find datasets with the EEGDash APIQuery the catalogue, filter by task or modality, list candidates.

Load one EEG recordingResolve a single record to an MNE Raw with channels and events.

EEG recording to PyTorch DataLoaderWrap braindecode windows in a DataLoader for model training.

Preprocess EEG and create windowsFilter, resample, epoch — and persist the windowed dataset.

Save and reload prepared dataCache a windowed dataset to disk and reattach it without recompute.

Download a dataset locallyPrefetch BIDS files to a local cache and validate the layout.

Swap any load_dataset(...) call for nm000207 to reproduce the tutorial on this dataset.

Citation

Simon Kojima, Shin'ichiro Kanoh (2024). Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing.

Provenance

¹Contributed to nemar in BIDS format.

²Curated & ingested by the EEGDash catalog; see CITATION.cff for canonical reference.

Related & sibling datasets

NM000193EEG · 11 subjSame authors NM000234EEG · 21 subj NM000190EEG · 10 subj NM000192EEG · 11 subj NM000189EEG · 10 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC0-1.0 · DOI not on file

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000207`
Title	Kojima et al. 2024 (Dataset B) — Four-class ASME BCI: investigation of the feasibility and comparison of two strategies for multiclassing
Author (year)	`Kojima2024B_P300`
Canonical	—
Importable as	`NM000207`, `Kojima2024B_P300`
Year	2024
Authors	Simon Kojima, Shin’ichiro Kanoh
License	CC0-1.0
Citation / DOI	Unknown
Source links	OpenNeuro \| NeMAR \| Source URL

NM000207: eeg dataset, 15 subjects#

Quickstart#

About This Dataset#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#