Improve of Neonatal Seizure Detection based on EEG Signal using K-mean clustering

Seizures are one of the most frequent medical emergencies. They are identified by visual electroencephalography (EEG) results assessment, and neuroscientific professionals are responsible for their care. This method takes a long time, and the results are inconsistent. A system for identifying epileptic seizures from EEG data that is collected from healthy individuals and epileptic patients is presented in this research to solve this issue. This system is based on a study of EEG data utilizing the Discrete Wavelet Transform (DWT) and both linear and nonlinear classifiers, Neonatal human EEG recordings are included in the dataset used in proposed model. A 19-channel EEG equipment was used to record the brainwave activity of 79 term newborns referred to the NICU at the Helsinki University Hospital. Five patients with structural seizure and non-seizure annotations were chosen for the experimental studies from these databases. Three experts independently identified the presence of seizures and non-seizures in the EEGs using visual interpretation, while statistical features were retrieved using the K-mean algorithm and the Least-Squares Support Vector Machine (LS-SVM) was utilized to identify seizures. To improve the model’s performance, (statistical and Hjorth and zero crossing) features were extracted, K-means’ feature selection using LS-SVM, and obtaining high accuracy 99.58% by P3-O1.