Abstract
dc:description.abstractEpilepsy is a complex neurological disorder characterized by recurrent seizures. An electroencephalogram (EEG) is typically used in the diagnosis of Epilepsy. Normally, EEGs are reviewed and analyzed by trained neurologists, but this can be time-consuming and error-prone. In this paper, we propose combining multiple classifiers in a multi-level fashion using stacked generalization to develop an effective solution for the detection of epilepsy using EEG data. Different classifiers such as Random Forest (RF), Recurrent Neural Networks (RNN), and XGBoost (XGB) were tested. The method was evaluated using Children’s Hospital Boston and Massachusetts Institute of Technology (CHB-MIT) dataset. The experimental results demonstrated that the proposed method outperforms existing methods, and achieved an accuracy of 96.166%.
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Computer Science
- Level thesis:degree_level
- Project
- Discipline thesis:degree_discipline
- School of Computer Science and Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Murugesan, Balamurugan
- Contributors dc:contributor
-
- Salloum, Ronald
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://scholarworks.lib.csusb.edu/etd/1384