EEGDash/nm000103

---
pretty_name: "Healthy Brain Network EEG - Not for Commercial Use"
license: cc-by-nc-sa-4.0
tags:
- eeg
- neuroscience
- eegdash
- brain-computer-interface
- pytorch
size_categories:
- 1K<n<10K
task_categories:
- other
---

# Healthy Brain Network EEG - Not for Commercial Use

**Dataset ID:** `nm000103`

_Shirazi2017_

**Canonical aliases:** `HealthyBrainNetwork` · `HBN_EEG_NC` · `HBN_NoCommercial`

> **At a glance:** EEG · 447 subjects · 3522 recordings · CC-BY-NC-SA 4.0

## Load this dataset

This repo is a **pointer**. The raw EEG data lives at its canonical source
(OpenNeuro / NEMAR); [EEGDash](https://github.com/eegdash/EEGDash) streams it
on demand and returns a PyTorch / braindecode dataset.

```python
# pip install eegdash
from eegdash import EEGDashDataset

ds = EEGDashDataset(dataset="nm000103", cache_dir="./cache")
print(len(ds), "recordings")
```

You can also load it by canonical alias — these are registered classes in `eegdash.dataset`:

```python
from eegdash.dataset import HealthyBrainNetwork
ds = HealthyBrainNetwork(cache_dir="./cache")
```

If the dataset has been mirrored to the HF Hub in braindecode's Zarr layout,
you can also pull it directly:

```python
from braindecode.datasets import BaseConcatDataset
ds = BaseConcatDataset.pull_from_hub("EEGDash/nm000103")
```

## Dataset metadata

| | |
|---|---|
| **Subjects** | 447 |
| **Recordings** | 3522 |
| **Tasks (count)** | 10 |
| **Channels** | 129 (×3522) |
| **Sampling rate (Hz)** | 500 (×3522) |
| **Total duration (h)** | 285.0 |
| **Size on disk** | 250.3 GB |
| **Recording type** | EEG |
| **Source** | nemar |
| **License** | CC-BY-NC-SA 4.0 |

## Links

- **DOI:** [10.82901/nemar.nm000103](https://doi.org/10.82901/nemar.nm000103)
- **NEMAR:** [nm000103](https://nemar.org/dataexplorer/detail?dataset_id=nm000103)
- **Browse 700+ datasets:** [EEGDash catalog](https://huggingface.co/spaces/EEGDash/catalog)
- **Docs:** <https://eegdash.org>
- **Code:** <https://github.com/eegdash/EEGDash>

---

_Auto-generated from [dataset_summary.csv](https://github.com/eegdash/EEGDash/blob/main/eegdash/dataset/dataset_summary.csv) and the [EEGDash API](https://data.eegdash.org/api/eegdash/datasets/summary/nm000103). Do not edit this file by hand — update the upstream source and re-run `scripts/push_metadata_stubs.py`._

pretty_name: "健康大脑网络脑电图数据集——非商业用途"
license: CC-BY-NC-SA 4.0
tags:
- 脑电图(EEG)
- 神经科学
- EEGDash
- 脑机接口
- PyTorch
size_categories:
- 1000 < 样本量 < 10000
task_categories:
- 其他

# 健康大脑网络脑电图数据集——非商业用途

**数据集ID**：`nm000103`

_Shirazi等人，2017年_

**标准别名**：`HealthyBrainNetwork` · `HBN_EEG_NC` · `HBN_NoCommercial`

> **概览**：脑电图(EEG) · 447名受试者 · 3522条记录 · CC-BY-NC-SA 4.0协议

## 加载该数据集

本仓库仅为**索引指针**。原始脑电图数据存储于其官方源（OpenNeuro / NEMAR）；[EEGDash](https://github.com/eegdash/EEGDash) 可按需流式加载该数据集，并返回PyTorch / braindecode格式的数据集。

python
# 安装eegdash库
from eegdash import EEGDashDataset

ds = EEGDashDataset(dataset="nm000103", cache_dir="./cache")
print(len(ds), "条记录")

你也可以通过标准别名加载该数据集——这些别名是`eegdash.dataset`中注册的类：

python
from eegdash.dataset import HealthyBrainNetwork
ds = HealthyBrainNetwork(cache_dir="./cache")

若该数据集已按照braindecode的Zarr格式镜像至Hugging Face Hub，你也可以直接拉取：

python
from braindecode.datasets import BaseConcatDataset
ds = BaseConcatDataset.pull_from_hub("EEGDash/nm000103")

## 数据集元数据

| 项 | 详情 |
|---|---|
| **受试者数量** | 447 |
| **记录条数** | 3522 |
| **任务（数量）** | 10 |
| **通道数** | 129条（共3522条记录） |
| **采样率（Hz）** | 500Hz（共3522条记录） |
| **总时长（小时）** | 285.0小时 |
| **磁盘占用大小** | 250.3 GB |
| **记录类型** | 脑电图(EEG) |
| **数据源** | NEMAR |
| **授权协议** | CC-BY-NC-SA 4.0 |

## 相关链接

- **DOI**：[10.82901/nemar.nm000103](https://doi.org/10.82901/nemar.nm000103)
- **NEMAR**：[nm000103](https://nemar.org/dataexplorer/detail?dataset_id=nm000103)
- **浏览700+数据集**：[EEGDash数据集目录](https://huggingface.co/spaces/EEGDash/catalog)
- **文档**：<https://eegdash.org>
- **代码仓库**：<https://github.com/eegdash/EEGDash>

---

_本内容由[dataset_summary.csv](https://github.com/eegdash/EEGDash/blob/main/eegdash/dataset/dataset_summary.csv)与[EEGDash API](https://data.eegdash.org/api/eegdash/datasets/summary/nm000103)自动生成。请勿手动编辑此文件——请更新上游源数据并重新运行`scripts/push_metadata_stubs.py`脚本。_