brain-computer interfaces

To address the challenges faced by patients with neurodegenerative disorders, Brain-Computer Interface (BCI) solutions are being developed. However, many current datasets lack inclusion of languages spoken by patients, such as Telugu, which is spoken by over 90 million people in India. To bridge this gap, we have created a dataset comprising Electroencephalograph (EEG) signal samples of commonly used Telugu words. Using the Open-BCI Cyton device, EEG samples were captured from volunteers as they pronounced these words.


Abstract— Objective: Recently, pupil oscillation synchronized with a steady visual stimulus was employed for an input of an interface. The system is inspired by steady-state visual evoked potential (SSVEP) BCIs, but it eliminates the need for contact with the participant because it does not need electrodes to measure electroencephalography. However, the stimulation frequency is restricted to being below 2.5 Hz because of the mechanics of pupillary vibration and information transfer rate (ITR) is lower than SSVEP BCIs.


Dataset description

This dataset contains EEG signals from 73 subjects (42 healthy; 31 disabled) using an ERP-based speller to control different brain-computer interface (BCI) applications. The demographics of the dataset can be found in info.txt. Additionally, you will find the results of the original study broken down by subject, the code to build the deep-learning models used in [1] (i.e., EEG-Inception, EEGNet, DeepConvNet, CNN-BLSTM) and a script to load the dataset.

Original article:


The EEG data were acquired from 16 healthy young adults (age range 22 - 30 years) with no neurological, physical, or psychiatric illness history. All the participants were naive BCI users who had not participated in any related experiments before. Informed consent was received from all participants.   



This material is associated with the PhD Thesis of Javier Olias (which is supervised by Sergio Cruces) and the article: 

EEG Signal Processing in MI-BCI Applications with Improved Covariance Matrix Estimators” by J.Olias, R. Martin-Clemente, M.A. Sarmiento-Vega and S. Cruces,
which was accepted in 2019 by IEEE Transactions on Neural Systems and Rehabilitation Engineering.