Ensuring road safety is becoming more and more significant for researchers and for all the society. One of the main issues in this area considers driver drowsiness. This study investigates the performance of Logistic Regression and Support Vector Machine (SVM) machine learning methods for drowsiness detection in drivers through EEG signal analysis. We extracted a sub-dataset named MPM39 from the “TRYOUT” dataset which features data from a 61-year-old female subject. Researchers collected EEG signals from multiple electrodes throughout a driving test to create the MPM39 dataset. Our methodology contained multiple data preprocessing steps which involved handling missing values and transforming categorical variables. The processed data served as the foundation for implementing and training both Logistic Regression and SVM models. The study assessed model performance through metrics such as precision, recall, F1-score, and accuracy. The research results show how machine learning technologies can improve road safety through precise detection of drowsy drivers. Logistic Regression proved to be the best model for detecting drowsiness from EEG data which supports driver behaviour monitoring.