Year: 2024
Type: dissertation
Abstract: Automated seizure detection from the electroencephalograms (EEG) signals plays an important role in epilepsy diagnosis. Although many approaches have shown their abilities in detecting seizure with scalp EEG, they have to face the issue of data insufficiency since the clinical scalp EEG signals are expensive and inconvenient to collect. Recently, wearable devices provide a much easier and cheaper way to collect EEG and therefore make it possible to monitor seizure in daily life. However, learning directly from wearable data is nontrivial since annotation of wearable data is often limited because the ground truth is only defined on scalp EEG. When labelled data is scarce, it becomes difficult to train a well performed detection framework. To remedy this issue, this project establish an automated seizure detection framework that leverage the unannotated wearable data as well as available annotated scalp data.
Source: Lirias
Author: Zhang, Jingwei
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W6983617271
Cites:
Cited by:
Related to: