Epilepsy Seizure Detection via Optimized Kernel Extreme Learning Machine Method

Epilepsy is a neurological disease that can have an impact on the health of patients. Therefore, the detection of epilepsy diseases is very important. In this paper, empirical mode decomposition is used to decompose epileptic EEG signals, and mixed features are extracted from signal components that contain more feature information. Linear feature mean, fluctuation index, and nonlinear feature sample entropy constitute the feature vectors for epileptic EEG classification. After that, an adaptive sparrow search algorithm is used to optimize the kernel based extreme learning machine for classification, and a five fold cross validation method is used to ensure the performance of the classifier. Experimental results show that the method proposed in this paper has a high accuracy and better performance.