International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 185 - Issue 15 |
Published: Jun 2023 |
Authors: Alina Ahsan, Sifatullah Siddiqi |
![]() |
Alina Ahsan, Sifatullah Siddiqi . Diagnosis and Prognosis: Prediction of Epilepsy using EEG Signals in Combination with Machine Learning Classifiers. International Journal of Computer Applications. 185, 15 (Jun 2023), 30-37. DOI=10.5120/ijca2023922841
@article{ 10.5120/ijca2023922841, author = { Alina Ahsan,Sifatullah Siddiqi }, title = { Diagnosis and Prognosis: Prediction of Epilepsy using EEG Signals in Combination with Machine Learning Classifiers }, journal = { International Journal of Computer Applications }, year = { 2023 }, volume = { 185 }, number = { 15 }, pages = { 30-37 }, doi = { 10.5120/ijca2023922841 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2023 %A Alina Ahsan %A Sifatullah Siddiqi %T Diagnosis and Prognosis: Prediction of Epilepsy using EEG Signals in Combination with Machine Learning Classifiers%T %J International Journal of Computer Applications %V 185 %N 15 %P 30-37 %R 10.5120/ijca2023922841 %I Foundation of Computer Science (FCS), NY, USA
Epilepsy is a type of neurological disorder which impacts the brain’s central nervous system. While the effects vary from person to person, they com- monly include mental instability, moments of loss of awareness, and seizures.There are several classi- cal approaches for analysing EEG signals for seizures identification, all of which are time-consuming. Many seizure detection strategies based on machine learning techniques have recently been developed to replace traditional methods. A hybrid model for seizure prediction of 54-DWT mother wavelets analysis of EEG signals using GA (genetic algorithm) in combination with other five machine learning (ML) classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Net- work (ANN) Naive Bayes (NB) and Random Forest is used in this paper.Using these 5 ML classifiers, the efficacy of 14 possible combinations for two-class epileptic seizure detection is evaluated. Nonetheless, the ANN classifier beat the other classifiers in most dataset combinations and attained the highest accuracy.