ArEEG: an Open-Access Arabic Inner Speech EEG Dataset.

Area of Science:

• Neuroscience
• Human-Computer Interaction
• Signal Processing

Background:

• Brain-Computer Interface (BCI) technology is increasingly focusing on inner speech over motor imagery for intuitive device control.
• Existing BCI datasets often require numerous electrodes, hindering the development of cost-effective and accessible systems.
• A scarcity of publicly available datasets limits research and development in this field.

Purpose of the Study:

• To introduce a novel, open-access Arabic Inner Speech dataset for Electroencephalographic (EEG) research.
• To provide a multi-class dataset (five commands) recorded with a minimal number of electrodes (eight) for economical BCI development.
• To facilitate BCI integration in Arabic-speaking regions and advance neurotechnology.

Main Methods:

• Development of a new Arabic Inner Speech dataset.
• Recording EEG data using eight electrodes.
• Classification of five distinct inner speech commands.

Main Results:

• A new, cost-effective, multi-class Arabic Inner Speech EEG dataset was created.
• The dataset utilizes only eight electrodes, offering an economical approach to BCI development.
• The dataset includes five distinct classes, exceeding the typical number in existing datasets.

Conclusions:

• The developed dataset addresses the need for accessible and economical BCI resources.
• This contribution supports the advancement of neurotechnology and BCI applications in Arabic-speaking communities.
• The open-access dataset will foster further research and innovation in language-specific BCI development.