Jadhav, Pranit N
(2016)
Automated and Reliable Low-Complexity SoC Design Methodology for EEG Artefacts Removal.
Masters thesis, Indian Institute of Technology Hyderabad.
Abstract
EEG is a non-invasive tool for neurodevelopmental disorder diagnosis (NDD) and treatment. However,
EEG signal is mixed with other biological signals including Ocular and Muscular artefacts making
it difficult to extract the diagnostic features. Therefore, the contaminated EEG channels are often discarded
by the medical practitioners which may result in less accurate diagnosis. Independent Component
Analysis (ICA) and wavelet-based algorithms require reference electrodes, which will create discomfort
to the patient/children and cause hindrance to the diagnosis of the NDD and Brain Computer Interface
(BCI). Therefore, it would be ideal if these artefacts can be removed real time and on hardware platform
in an automated fashion and denoised EEG can be used for online diagnosis in a pervasive personalised
healthcare environment without the need of any reference electrode. In this thesis we propose a reliable,
robust and automated methodology to solve the aforementioned problem and its subsequent hardware
implementation results are also presented. 100 EEG data from Physionet, Klinik fur Epileptologie, Universitat
Bonn, Germany, Caltech EEG databases and 3 EEG data from 3 subjects from University of
Southampton, UK have been studied and nine exhaustive case studies comprising of real and simulated
data have been formulated and tested. The performance of the proposed methodology is measured in
terms of correlation, regression and R-square statistics and the respective values lie above 80%, 79% and
65% with the gain in hardware complexity of 64.28% and hardware delay 53.58% compared to state-ofthe
art approach. We believe the proposed methodology would be useful in next generation of pervasive
healthcare for BCI and NDD diagnosis and treatment.
Actions (login required)
 |
View Item |
Altmetric
Altmetric