A New Method for EEG signals Classification Based on RBF NN

Abstract

Automation is necessary since traditional EEG assessments are tedious and time-consuming, particularly the outpatient kind. For this manuscript, the researchers focused on constructing a three-class EEG classifier using FeExt and RBFNN, which stands for Radial Basis Functional Neural Network. If FeExt is finished, RBFnn may be trained to equally recognize the trends. Seizure signals are one of the various anomalies that may be identified using the EEG signal. Stable, interactive, and seizure signals are the three different types of EEG signals. This manuscript's goal is to classify EEG signals using RBFnn. EEG signal data were relied on the CHB-MIT Scalp EEG dataset. There are 55 various FeExt schemes investigated, and a classifier is constructed that is relatively quick and accurate. The 10 morphological features of the literature were not explored or compared with the extraction techniques. According to research, the multilayer perceptron with momentum learning rule is the best classifier topology, and the FeExt algorithms PCA, Bi-gonal 2.2, coif1, DCT, db9, Re-Bi-gonal 1.1, and sym2 perform better than others. The recorded results may be effectively classified for EEG rhythm for quick examination by a neurology professional. Therefore, quick, accurate diagnosis that saves time. Using a similar method, the EEG rhythm categorization for other brain illnesses may be used.