.png){kind=icon}
.png){kind=icon}
Return
Offline Analysis for Designing Electrooculogram Based Human Computer Interface Control for Paralyzed Patients
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2884411.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Currently, majority of persons were immobilized and need aid from caretakers due to disability. To reduce and overcome such problem, there was a need for developing human-computer interface (HCI) with the help of biosignals. In this paper, we propose a two-channel elecctrooculograpy (EOG)-based HCI to encourage the contact ability as well as value of life for paralyzed persons who cannot speak or shift their extremity by using 20 subjects with the help of ADT26 Bio amplifier. EOG signals were collected for 11 tasks from both vertical and horizontal eye movement by using gold-platted electrodes. The extracted EOG signals were processed with convolution and Plancherel theorem to obtain the features. Layered recurrent neural network (LRNN) was implemented to analyze the extracted features and then converted into a sequence of commands to control the HCI. A graphical user interface was developed using MATLAB to help a user to convey their thoughts. This paper shows an average classification accuracy of 90.72% for convolution features and 91.28% for Plancherel features. Off-line single trail analysis was also performed to analyze the recognition accuracy of the proposed HCI system. The off-line analysis displayed that Plancherel features using LRNN were high compared to convolution features using LRNN. From this paper, we found that LRNN architecture using Plancherel features was more suitable for developing EOG-based HCI. Single trail analysis was conducted to identify the recognizing accuracy in offline. The off-line results indicated that in comparison with other EOG-based HCI systems, our system was user friendly and needs minimum training to operate.
Keywords:
Elecctrooculograpy
human computer interface
layered recurrent neural network
amyotrophic lateral sclerosis
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
View more organizations