A mouse control system based on EOG for human-computer interface

Abstract

The current population of paralyzed people in Taiwan is about 360 000 The main symptoms are loss of mobility dexterity and autonomous control The principle of the human-computer interface (HCI) provides a bridge for communication between the user and the computer After visual stimulation or feedback the user can use different control methods to manipulate the computer This research used electrooculogram (EOG) as the control signal in two configurations which differed from common configuration to develop an EOG-based features recognition system software and combine with a graphical user interface (GUI) for simulation of mouse control system Twelve people were recruited in this research Six of them were acquired EOG signal to implement system development The other six performed validation experiment which integrated the algorithm with the user interface In the test of the mouse control system the precision accuracy and time cost were used as indicators to evaluate the system performance of algorithms in two configurations The results showed that in the test winking detection and peak detection algorithm had achieved 100% accuracy for all subjects in both configurations and the accuracy of the classification algorithm had reached 83% above The time cost of each task for all subjects were between 15~35 second T-test (Student’s t-test) was performed to compare the performance of algorithms in different configurations The p-value was 0 13 for the accuracy of the classification algorithm and 0 23 for the time cost There was no significant difference between the results in different configurations In conclusion this research successfully developed a mouse control system based on EOG for human-computer interface which enabled normal subjects to use EOG to control the graphical user interface And there was no significant difference between the results in two configurations In the future patients with quadriplegia should be invited to test the system to improve system reliability

Date of Award	2021
Original language	English
Supervisor	Chou-Ching Lin (Supervisor)