Development of an expert multitask gadget controlled by voluntary eye movements

  • Authors:

  • T. Gandhi;M. Trikha;J. Santhosh;S. Anand

  • Affiliations:

  • Rehaibilation Engineering Laboratory, Centre for Biomedical Engineering, Indian Institute of Technology, Delhi and All India Institute of Medical Sciences, New Delhi, India;Rehaibilation Engineering Laboratory, Centre for Biomedical Engineering, Indian Institute of Technology, Delhi and All India Institute of Medical Sciences, New Delhi, India;Computer Service Centre, Indian Institute of Technology, Delhi, India;Rehaibilation Engineering Laboratory, Centre for Biomedical Engineering, Indian Institute of Technology, Delhi and All India Institute of Medical Sciences, New Delhi, India

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 12.06

Visualization

Abstract

Design of assistive technology using advanced soft computing techniques on proper hardware platform has been an important issue of research for the last two decades. In the present study, a novel scheme is presented to develop a multitask gadget controlled by eye movements for the disabled, especially for individuals with spinal injury disorders. Electro-oculogram (EOG) signals generated by horizontal, vertical and diagonal eye movements and blinks were measured using a pair of surface electrodes with respect to a reference electrode placed on forehead. After preprocessing, the acquired signals were amplified with AC-coupling in order to reduce unnecessary drifts. Classifier based on DFA (Deterministic Finite Automata) was developed by using VHDL to discriminate 128 different EOG states from processed horizontal and vertical eye signals based on threshold settings specific to individuals. Later, online viability of the system was established by conducting some experiments on normal as well as disabled subjects. The utility of the proposed method was enhanced by implementing a robust algorithm for signal classification and training both the subjects and the device. It was found that with the proposed scheme, the accuracy of the detection and control of the specified gadget is 95.33%, with sensitivity and specificity as 95.6% and 95%, respectively. The proposed model can be used for designing smart houses for the disabled and elderly.