Electro-oculogram based digit recognition to design assitive communication system for speech disabled patients

Abstract

HCI (Human Computer Interfacing) technology is now able to provide an alternative support to the speech disabled person who have undergone severe brain stroke or spinal cord injury. It has been presented here that amongst all bio potential signal Electro-Oculogram (EOG) signal has got the ability to represent all daily life characters which is most needed for communication. This paper is aimed to provide novel approach of rehabilitative HCI where it successfully classifies the numerical digits drawn by subject's eye movement and for achieving the result, electro-oculography sensors (dual channel) and amplifier has been designed, which is able to extract the sharp change of corneo retinal potential due to eyeball movement intended to draw a pattern (numeric digit, alphabet). The extracted signal has been processed and classified successfully with more than 90% accuracy rate and with suitable precision and sensitivity value. Here Power spectral density has been used as feature extractor and support vector machine with multilayer perceptron kernel function has been used as feature classifier. Performance of other classifiers also have been compared here. 12 healthy subjects took part in experiment and their eyeball movement signal has been acquired for distinguishing different numerical digits that are frequently needed for communication to external world.