Datasets
Standard Dataset
IIST BCI Dataset-5 for Malayalam Vowels and Consonants
- Citation Author(s):
- Submitted by:
- Nancy Sunil
- Last updated:
- Sat, 05/11/2024 - 02:23
- DOI:
- 10.21227/qw2m-jn47
- Data Format:
- License:
- Categories:
- Keywords:
Abstract
This paper presents a dataset of brain Electroencephalogram (EEG) signals created when Malayalam vowels and consonants are spoken. The dataset was created by capturing EEG signals utilizing the OpenBCI Cyton device while a volunteer spoke Malayalam vowels and consonants. It includes recordings obtained from both sub-vocal and vocal. The creation of this dataset aims to support individuals who speak Malayalam and suffer from neurodegenerative diseases. Moreover, this dataset is expected to advance brain-computer interface technology and has potential in developing effective communication solutions for individuals with limited verbal abilities.
Instructions:
The raw dataset comprises text documents, with EEG samples stored as files containing values separated by commas and arranged in rows and columns. Each row represents a specific sample.
The first column denoting the sample index.
Columns 2 to 9 containing EEG recordings from eight selected channels.
Columns ranging from 10 to 22 and 24, may hold supplementary or unimportant data.
The 23rd column typically represents time in a raw, unprocessed format.
25th column displays timestamps in the format "YearMonth-Day Hour:Minute:Second". These timestamps provide precise temporal information for each sample, aiding in synchronization with external events or measurements.
Alongside EEG data, the text documents may contain metadata or supplementary information relevant to the recordings. This structured format facilitates efficient processing and analysis of EEG data for various research or clinical applications.