Title: Brain - Computer Interface for Communication via Record Electrophysiological Signals

Year of Publication: Dec - 2015
Page Numbers: 69-76
Authors: Svetla Radeva, Dimitar Radev
Conference Name: The Second International Conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC2015)
- United Arab Emirates

Abstract:


The brain-computer interface (BCI) aim to use Electroencephalography (EEG) activity or other electrophysiological measures of brain functions as new non-muscular channels for communication with different smart devices for disabled persons. For connection with different smart devices was used recorded with experimental setup electrophysiological signals for execution of five different mental tasks. BCI records brain signals and processes them to produce device commands. This signal processing has two stages. The first stage is feature extraction and calculation of the values of specific features of the signals. The second stage is a translation algorithm that translates these features into device commands. Processed signals after noise filtering, clustering and classification with Bayesian Network classifier and pair-wise classifier was estimated and put into brain-computer interface for connection with smart devices.