EEGdash›NeMAR›NM000276

Iss. 276 · 40 subjects · 40 recordings · CDLA-Permissive-2.0

Dataset Brief · SWEC iEEG Dataset

NM000276: ieeg dataset, 40 subjects#

Name: SWEC iEEG Dataset
Published: 2025-01-01
License: CDLA-Permissive-2.0

SWEC iEEG Dataset

Access recordings and metadata through EEGDash.

Citation: Francesco Carzaniga, Michael Hersche, Abu Sebastian, Kaspar Schindler, Abbas Rahimi (2025). SWEC iEEG Dataset. 10.82901/nemar.nm000276

Modality: ieeg Subjects: 40 Recordings: 40 License: CDLA-Permissive-2.0 Source: nemar

Metadata: Complete (100%)

40-participant iEEG dataset — SWEC iEEG Dataset.

Data & curation Francesco Carzaniga · Michael Hersche · Abu Sebastian · Kaspar Schindler · Abbas Rahimi
Senior author Abbas Rahimi
Year 2025 · Distributed via NeMAR

iEEG · 32 (5), 64 (3), 56 (2), 54 (2), 34 (2), 24 (2), 60, 39, 49, 66, 98, 104, 22, 40, 62, 86, 69, 33, 74, 47, 89, 76, 57, 42, 63, 88, 48, 61, 29, 75 ch512, 1024 HzBIDS 1.9.0Task · ltm

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 NM000276

dataset = NM000276(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 = NM000276(cache_dir="./data", subject="01")

Advanced query

dataset = NM000276(
    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{nm000276,
  title = {SWEC iEEG Dataset},
  author = {Francesco Carzaniga and Michael Hersche and Abu Sebastian and Kaspar Schindler and Abbas Rahimi},
  doi = {10.82901/nemar.nm000276},
  url = {https://doi.org/10.82901/nemar.nm000276},
}

§ 02Study · The README

About This Dataset#

Long-term pre-surgical intracranial EEG (iEEG) from patients with

pharmacoresistant epilepsy, recorded at the Sleep-Wake-Epilepsy-Center (SWEC), Department of Neurology, Inselspital, University of Bern, in collaboration with the Integrated Systems Laboratory, ETH Zurich.

The public SWEC release is FULLY ANONYMIZED. Anatomical channel labels and

electrode locations are NOT disclosed (electrode coordinates + the implied imaging would be re-identifying for epilepsy-surgery patients). Channels are therefore named iEEG01..iEEGNN, preserving the original recording order (1:1 with the source channel index 0..N-1). electrodes.tsv lists every contact with coordinates set to n/a, and channel type is recorded as the generic intracranial SEEG (the per-contact strip/grid/depth type is not disclosed). No locations were fabricated.

DOI

SWEC iEEG Dataset (BIDS)

Provenance

Converted to BIDS from the public HDF5 release at https://mb-neuro.medical-blocks.ch/public_access/databases/ieeg/swec_ieeg (authentic medical-blocks / artorg source). This BIDS dataset re-hosts the 40-subject / 378-file public subset.

How to cite

Carzaniga, F., Hersche, M., Sebastian, A., Schindler, K. & Rahimi, A. “A foundation model with multi-variate parallel attention to generate neuronal activity.” arXiv:2506.20354 (2025). https://doi.org/10.48550/arXiv.2506.20354 SWEC-ETHZ iEEG Database: http://ieeg-swez.ethz.ch/

License

Community Data License Agreement – Permissive, Version 2.0 (CDLA-Permissive-2.0).

NEMAR Metadata#

[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000276-blue)](https://doi.org/10.82901/nemar.nm000276) # SWEC iEEG Dataset (BIDS) Long-term pre-surgical intracranial EEG (iEEG) from patients with pharmacoresistant epilepsy, recorded at the Sleep-Wake-Epilepsy-Center (SWEC), Department of Neurology, Inselspital, University of Bern, in collaboration with the Integrated Systems Laboratory, ETH Zurich. ## Contents - Subjects: 40 - Total recording: 5376 hours of continuous iEEG - Annotated electrographic seizures: 381 - Task label: ltm (long-term monitoring; passive, no task) - Format: BrainVision (IEEE float32), data in microvolts (µV) ## Recording & preprocessing (at source) - Intracranial strip, grid, and depth electrodes (mixed). - 16-bit analog-to-digital conversion. - Sampling rate 512 Hz or 1024 Hz (per subject; see participants.tsv). - Digitally band-pass filtered 0.5-150 Hz (4th-order Butterworth, forward-backward / zero-phase). - Channels with artifacts were removed at the source; remaining channels marked good. - Median reference across channels (per the SWEC-ETHZ long-term protocol). - Seizure onsets/offsets annotated by board-certified epileptologist Prof. Kaspar Schindler. ## Anonymization — channels & electrodes The public SWEC release is FULLY ANONYMIZED. Anatomical channel labels and electrode locations are NOT disclosed (electrode coordinates + the implied imaging would be re-identifying for epilepsy-surgery patients). Channels are therefore named iEEG01..iEEGNN, preserving the original recording order (1:1 with the source channel index 0..N-1). electrodes.tsv lists every contact with coordinates set to n/a, and channel type is recorded as the generic intracranial SEEG (the per-contact strip/grid/depth type is not disclosed). No locations were fabricated. ## Provenance Converted to BIDS from the public HDF5 release at https://mb-neuro.medical-blocks.ch/public_access/databases/ieeg/swec_ieeg (authentic medical-blocks / artorg source). This BIDS dataset re-hosts the 40-subject / 378-file public subset. ## How to cite Carzaniga, F., Hersche, M., Sebastian, A., Schindler, K. & Rahimi, A. “A foundation model with multi-variate parallel attention to generate neuronal activity.” arXiv:2506.20354 (2025). https://doi.org/10.48550/arXiv.2506.20354 SWEC-ETHZ iEEG Database: http://ieeg-swez.ethz.ch/ ## License Community Data License Agreement – Permissive, Version 2.0 (CDLA-Permissive-2.0).

License: CDLA-Permissive-2.0

Authors:

Francesco Carzaniga
Michael Hersche
Abu Sebastian
Kaspar Schindler
Abbas Rahimi

Versions:

Version	DOI	Released
`current`	10.82901/nemar.nm000276

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Channel counts (ch)

2224293233343940424748495456576061626364666974757686888998104

Sampling frequencies (Hz)

5121024

Total recording duration: 5376 h

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 32 (5), 64 (3), 56 (2), 54 (2), 34 (2), 24 (2), 60, 39, 49, 66, 98, 104, 22, 40, 62, 86, 69, 33, 74, 47, 89, 76, 57, 42, 63, 88, 48, 61, 29, 75 ch · iEEG · 512, 1024 Hz · 40 subjects, 40 recordings

Live trace viewer — sub-01 · task-ltm

Showing one representative recording out of 40 subjects and 40 recordings in this dataset. Browse the full set on OpenNeuro; drop any other _ieeg.{set,edf,bdf,vhdr} file onto the viewer (or pass ?ieeg=<url>) to inspect it.

No scalp electrode layout is currently indexed for this dataset. Once the eegdash montage registry ingests it, the interactive viewer will appear here automatically.

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.NM000276(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)—

Canonical—

Importable asNM000276

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

class eegdash.dataset.NM000276(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

SWEC iEEG Dataset

Study:: nm000276 (NeMAR)
Author (year):: —
Canonical:: —

Also importable as: NM000276.

Modality: ieeg; Subject type: Unknown. Subjects: 40; recordings: 40; 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/nm000276 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000276 DOI: https://doi.org/10.82901/nemar.nm000276

Examples

>>> from eegdash.dataset import NM000276
>>> dataset = NM000276(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 — NM000276.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 nm000276 to reproduce the tutorial on this dataset.

Citation

Francesco Carzaniga, Michael Hersche, Abu Sebastian, Kaspar Schindler, Abbas Rahimi (2025). SWEC iEEG Dataset. 10.82901/nemar.nm000276

Provenance

¹Contributed to nemar in BIDS format.

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

³Persistent identifier: 10.82901/nemar.nm000276.

Related & sibling datasets

ON005007IEEG · 40 subj ON006519IEEG · 21 subj ON004127IEEG · 8 subj ON005931IEEG · 8 subj ON003078IEEG · 6 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

channels · electrodes · coordsystem

Provenance

CDLA-Permissive-2.0 · 10.82901/nemar.nm000276

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000276`
Title	SWEC iEEG Dataset
Author (year)	—
Canonical	—
Importable as	`NM000276`
Year	2025
Authors	Francesco Carzaniga, Michael Hersche, Abu Sebastian, Kaspar Schindler, Abbas Rahimi
License	CDLA-Permissive-2.0
Citation / DOI	10.82901/nemar.nm000276
Source links	OpenNeuro \| NeMAR \| Source URL

NM000276: ieeg dataset, 40 subjects#

Quickstart#

About This Dataset#

NEMAR Metadata#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#