Development of Brain Computer Interface (BCI) system for integration with Functional Electrical Stimulation (FES) application

Brain-Computer Interface (BCI) is a communication tool that translates human desire for other devices. The intention is for the majority of patients who were not able to move as stroke, spinal cord injury and traumatic brain injury. The goal of this study was to develop and analysis of offline and r...

Full description

Saved in:
Bibliographic Details
Main Author: Ahad, Rosnee
Format: Thesis
Language:English
English
English
Published: 2015
Subjects:
Online Access:http://eprints.uthm.edu.my/1447/2/RIHAB%20SALAH%20KHAIRI%20COPYRIGHT%20DECLARATION.pdf
http://eprints.uthm.edu.my/1447/1/24p%20RIHAB%20SALAH%20KHAIRI.pdf
http://eprints.uthm.edu.my/1447/3/RIHAB%20SALAH%20KHAIRI%20WATERMARK.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Brain-Computer Interface (BCI) is a communication tool that translates human desire for other devices. The intention is for the majority of patients who were not able to move as stroke, spinal cord injury and traumatic brain injury. The goal of this study was to develop and analysis of offline and realtime Brain Computer Interface (BCI) system for integration with Functional Electrical Stimulation (FES) application. Here, the study using Electroencephalography (EEG) system for beta wave. PowerLab 8/35 and Dual Bio Amp as the detector signal the brain that will be used in this study. While, for analyze the offline data, LabChart and Matlab software was used but Digital Filter was used to extract the data. Values from statistic of beta band for EEG signals were used as features for extraction. The selected features were classified by using Artificial Neural Network (ANN) application to obtain the maximum classification rate. The output of this study shows that values of standard deviation, standard error, minimum, end value – start value and RMS of the beta band for EEG signal is high for swing motion and low for static. For the hardware, Arduino Mega2560 board to be used as a controller before displayed to the led. Led is ON when the input is for swing motion and OFF when is static data. All result are achieve and same with the feature extraction. For the realtime data analyzes, signal from the PowerLab 8/35 and Dual Bio Amp will be amplified and rectified. The brain signal amplified from microvolt to volt and then to rectified from alternating current (ac) signal to direct current (dc) signal before to Matlab simulink and the Arduino board as a display output. The result obtained can be applied in the Functional Electrical Stimulation (FES) system with a little modification on the future where the simulink output is converted to the pulse signal.