Datasets
Standard Dataset
IIST BCI Dataset-7 for Human Space Missions
- Citation Author(s):
- Submitted by:
- Adithya Menon
- Last updated:
- Mon, 08/12/2024 - 14:14
- DOI:
- 10.21227/5tmq-dj77
- Data Format:
- License:
- Categories:
- Keywords:
Abstract
We developed a unique and valuable dataset specifically for advancing Brain-Computer Interface (BCI) systems by recording brain activity from a dedicated volunteer. The participant was asked to pronounce 100 carefully selected Malayalam words, along with their English translations, which were chosen for their relevance to astronauts during human space missions. The volunteer pronounced these words both vocally and subvocally, each word being repeated 50 times. Non-invasive Electroencephalography (EEG) sensors were employed to capture the brain activity associated with these tasks. This dataset holds significant potential for the future development of BCI applications, especially in enhancing communication for astronauts in space and offering innovative solutions for individuals with speech or motor impairments. By facilitating communication in challenging environments, this dataset could lead to groundbreaking advances in both space exploration and assistive technology.
- The raw dataset consists of text documents where EEG samples are stored as comma-separated values.
- Data is organized in rows and columns, with each row representing a distinct sample.
- The first column represents the sample index.
- Columns 2 to 9 contain EEG recordings from eight specific channels.
- Columns 10 to 22 and 24 may contain additional or less relevant data.
- The 23rd column generally holds time information in a raw, unprocessed format.
- The 25th column includes timestamps in the format "YearMonth-Day Hour:Minute:Second," providing precise temporal details for each sample.
- These timestamps help synchronize samples with external events or measurements.
- In addition to EEG data, the text documents may include metadata or other supplementary information.
- This structured format allows for efficient processing and analysis of EEG data for various research or clinical applications.