Brain Computer Interface for Neurodegenerative Person Using Electroencephalogram

Brain-computer interface (BCI) connects the outside world, in real time and in a natural way, like biological communication system. It facilitates the communication link from the brain to the external world by converting brain thoughts in to control commands to control the external devices, such as...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.2439-2452
Main Authors: Junwei, Li, Ramkumar, S., Emayavaramban, G., vinod, D. Franklin, Thilagaraj, M., Muneeswaran, V., Pallikonda Rajasekaran, M., Venkataraman, V., Hussein, Ahmed Faeq
Format: Article
Language:English
Subjects:
band power
Brain computer interface
Brain-computer interfaces
Classification
Communications systems
Education
Electric appliances
Electroencephalography
Feature extraction
FRDM-KL25Z
Household appliances
Human-computer interface
Keyboards
Mouse devices
Radial basis function
Support vector machines
Task analysis
Wheelchairs
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Brain-computer interface (BCI) connects the outside world, in real time and in a natural way, like biological communication system. It facilitates the communication link from the brain to the external world by converting brain thoughts in to control commands to control the external devices, such as wheelchair, keyboard mouse, and other home appliances. Measuring the electrical brain activity by placing electrodes over scalp is called electroencephalogram (EEG). By combining these two techniques, we are able to create EEG-based BCI. In this paper, we use band power and radial basis function to analyze the signal for four mentally composed tasks to design four states BCI for a neurodegenerative person using EEG. Online study was conducted to analyze the performance of the wheelchair for a neurodegenerative person. The result shows that an overall average classification accuracy of 92.50% and individual tasks with an average classification of 95%, 87.50%, 92.50%, and 95.00% were achieved for the four tasks. The result proves that control commands generated from the EEG signal have the bcapacity to control the intelligent systems.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2886708