Real Time Text Speller based on Eye Movement Classification Using Wearable EEG Sensors

Making the machine more empathic to the user is one of the aspects of affective computing. Signal procured by Brain Computer Interface frameworks are utilized to process brain signals for controlling different gadgets for human ease. P300 based content speller is one of the device utilized for eye-writing, however eye movement based content speller can create fine and exact comes about as contrasted with P300 based content speller. This paper presents a robust solution for utilizing eye muscular-movement for typing text content. Eye movement is a brawny and husky movement, yet by utilizing EEG signals for eye movements, we have obtained EEG signal for diverse users and after that utilizing those signals we have finally created a framework for content spelling as a cursor movement over the letter sets. All analysis were executed on runtime procured datasets of numerous users to arrange the indicator in three classes lastly utilizing them as an aide sign to spell the content. The accuracy of the proposed system for right movement, left movement and blink is 70%, 80% and 79% respectively.