EEG-Based Drivers Drowsiness Prediction Using Personalized Features Extraction and Classification Methods Under Python

During the last century, most of researchers tend to develop alternative solutions to variant fields’ problems using artificial intelligence and machine learning techniques, leading to an important AI revolution. Applying these techniques in healthcare was a big win, namely the importance of predicting the occurrence of seizures at a prompt time or detecting pathologies as earlier as possible. Moreover, the early detection of drowsiness state for drivers became a serious subject of interest, due to the important turnout for driving in addition to the increasing of cars accidents. So, increasing road safety was an obligation. Our paper therefore, presents several methods of detecting drivers’ drowsiness using personalized features extraction and machine learning algorithms applied to a single channel of electroencephalogram signals under Python.