Epileptic EEG Classification Using Synchrosqueezing Transform and Machine Learning

Epilepsy is one of the neurological diseases that occur incidences worldwide. The electroencephalography (EEG) recording method is the most frequently used clinical practice in the diagnosis and monitoring of epilepsy. Many computer-aided analysis methods have been developed in the literature to facilitate the analysis of long-term EEG signals. In the proposed study, the patient-based seizure detection approach is proposed using a high-resolution time-frequency (TF) representation named Synchrosqueezed Transform (SST) method. The SST of two different data sets called the IKCU data set and CHB-MIT data set are obtained, and Higher-order joint TF(HOJ-TF) based and Gray-level co-occurrence matrix (GLCM) based features are calculated using these SSTs. Using some machine learning methods such as Decision Tree (DT), k-Nearest Neighbor (kNN), and Logistic Regression (LR), classification processes are conducted. High patient-based seizure detection success is achieved for both the IKCU data set (94.25%) and the CHB-MIT data set (95.15%).