areeg-an-open-access-arabic-inner-speech-eeg-dataset

Repository contains all code needed to work with ArEEG dataset

https://github.com/eslam21/areeg-an-open-access-arabic-inner-speech-eeg-dataset

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 6 DOI reference(s) in README
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.1%) to scientific vocabulary

Keywords

eeg eeg-classification inner-speech
Last synced: 6 months ago · JSON representation ·

Repository

Repository contains all code needed to work with ArEEG dataset

Basic Info
  • Host: GitHub
  • Owner: Eslam21
  • License: gpl-3.0
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 1.02 GB
Statistics
  • Stars: 4
  • Watchers: 2
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Topics
eeg eeg-classification inner-speech
Created over 1 year ago · Last pushed 6 months ago
Metadata Files
Readme License Citation

README.md

🧠 ArEEG: An Open-Access Arabic Inner Speech EEG Dataset

Welcome to the official repository for ArEEG, the first open-access EEG dataset capturing inner speech in Arabic.
This dataset enables research in brain-computer interfaces (BCI), Arabic language processing, and neuro-linguistics.

The repository provides all the necessary code and scripts for:
- Data loading & preprocessing: dataloader.py
- Getting started quickly: areeg-starter.ipynb - Reproducing the experiments


🚀 Key Features

  • 👥 12 native Arabic participants (balanced gender distribution, aged 17–25)
  • 🧩 5 inner speech commands: Up, Down, Left, Right, Select
  • 🎧 8-channel EEG headset (Unicorn Hybrid Black+, 250 Hz sampling rate)
  • 🧪 4650 trials across 15 sessions per subject (one with 21 sessions)
  • 💻 Open-source preprocessing & ML pipelines (Python, NumPy, Pandas, Scikit-learn, MNE)
  • 🌍 First-ever open Arabic inner speech dataset for BCI research

📂 Dataset Access and Notebooks

The dataset is hosted publicly on:
- 📦 OpenNeuro
- 📊 Kaggle (data can be found in RecordedSessions folder)

To make it easy to get started, we provide a multi-version Kaggle notebook of preliminary results

Publication

📄 Official publication in Scientific Data (Nature)


📜 Citation

If you use the ArEEG dataset in your work, please cite it as follows:

bibtex @article{Metwalli2025, title = {ArEEG: an Open-Access Arabic Inner Speech EEG Dataset}, volume = {12}, ISSN = {2052-4463}, url = {http://dx.doi.org/10.1038/s41597-025-05387-w}, DOI = {10.1038/s41597-025-05387-w}, number = {1}, journal = {Scientific Data}, publisher = {Springer Science and Business Media LLC}, author = {Metwalli, Donia and Kiroles, Antony E. and Radwan, Yousef A. and Mohamed, Eslam Ahmed and Barakat, Mariam and Ahmed, Anas and Omar, Amr M. and Selim, Sahar}, year = {2025}, month = aug }

Owner

  • Name: Eslam Mohamed
  • Login: Eslam21
  • Kind: user
  • Location: Egypt

Just a nerd

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this dataset, please cite it using the following metadata."
title: "ArEEG: Arabic Inner Speech EEG dataset"
authors:
  - family-names: Metwalli
    given-names: Donia
  - family-names: Ahmed
    given-names: Eslam
  - family-names: Emil
    given-names: Antony
  - family-names: Radwan
    given-names: Yousef A.
  - family-names: Barakat
    given-names: Mariam
  - family-names: Ahmed
    given-names: Anas
  - family-names: Omar
    given-names: Amro
  - family-names: Selim
    given-names: Sahar
date-released: 2025-01-01
doi: 10.18112/openneuro.ds005262.v1.0.1
version: 1.0.1
repository-code: "https://openneuro.org/datasets/ds005262"
publisher: OpenNeuro

GitHub Events

Total
  • Watch event: 3
  • Push event: 11
  • Fork event: 1
Last Year
  • Watch event: 3
  • Push event: 11
  • Fork event: 1

Dependencies

requirements.txt pypi
  • numpy ==1.26.4
  • pandas ==2.1.4
  • scikit-learn ==1.2.2
  • scipy ==1.11.4