dc.contributor.author |
Supuni, H.D.S. |
|
dc.contributor.author |
Chathuranga, P.D.T. |
|
dc.contributor.author |
Chathuranga, L.L.G. |
|
dc.date.accessioned |
2022-04-18T08:35:14Z |
|
dc.date.available |
2022-04-18T08:35:14Z |
|
dc.date.issued |
2022-01-19 |
|
dc.identifier.issn |
1391-8796 |
|
dc.identifier.uri |
http://ir.lib.ruh.ac.lk/xmlui/handle/iruor/5678 |
|
dc.description.abstract |
An epileptic seizure is a symptom due to abnormal paroxysmal excessive neuronal activity in the cerebral cortex. Seizures are one of the symptoms leading to a diagnosis of a brain tumor in adults. Epilepsy is a tendency to have repeated epileptic seizures. The diagnosis is confirmed by detecting specific brain patterns of the electroencephalography (EEG). Existing work shows that epileptic seizures can be detected using machine learning methods with high accuracies. However, there is a need for classifying epileptic seizure patterns to predict possible tumors. In this paper, EEG data is used to predict possible brain tumors and classify epileptic seizure patterns using machine learning methods such as Random Forest, Logistic Regression, Naive-Bayes, and Neural Networks. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
Faculty of Science, University of Ruhuna, Matara, Sri Lanka |
en_US |
dc.subject |
Machine learning |
en_US |
dc.subject |
Epilepsy |
en_US |
dc.subject |
Electroencephalography (EEG) |
en_US |
dc.subject |
Neural networks |
en_US |
dc.subject |
Brain tumor |
en_US |
dc.title |
Performance evaluation of machine learning models for epileptic seizures and brain tumor prediction from EEG |
en_US |
dc.type |
Article |
en_US |