with seven electrodes was designed for an automated EEG-based AD detection system, and the SVM obtained 91.1% accuracy [35]. A portable EEG device was used to quantify the mental workload during the driving and the binary machine learning models achieved high accuracy (98.2% to 99.6%) between resting state and driving state [36]. Furthermore, a low-cost EEG system was developed to predict ischemic stroke events, and the SVM model obtained 92% accuracy [37]. In the automatic detection of epileptic EEG, ML framework based on RF combined with a grid search optimization technique achieved an accuracy of 96.7% [38].
