An automated and highly efficient driver drowsiness detection and alert system using electroencephalography signals for safe driving

The increasing frequency of vehicle accidents presents a significant challenge in our society. Unsafe behaviors, such as distracted driving (e.g., eating, texting, and talking on the phone), as well as fatigue, medication use, and driving under the influence, contribute to this rise. Drowsiness is a particularly concerning risk factor. This study proposes an automated driver drowsiness detection and warning system based on the Support Vector Machine (SVM) classifier. By analyzing EEG signals to measure the relative power ratio of alpha and beta waves, the system was validated using the renowned MIT-BIH polysomnographic database, which focuses on drowsiness research. Evaluation of the system demonstrates an average accuracy of \(\varvec{99,87\%}\) $\mathbf{99}\mathbf{,}\mathbf{87}\mathbf{\%}$ , achieving real-time detection in \(\varvec{1072,590}\) $\mathbf{1072}\mathbf{,}\mathbf{590}$ ms, a recall of \(\varvec{99,77\%}\) $\mathbf{99}\mathbf{,}\mathbf{77}\mathbf{\%}$ , and a false negative rate of \(\varvec{0,22\%}\) $\mathbf{0}\mathbf{,}\mathbf{22}\mathbf{\%}$ . These results highlight the precision and reliability of the proposed system, with an overall F-score of \(\varvec{99,88\%}\) $\mathbf{99}\mathbf{,}\mathbf{88}\mathbf{\%}$ . Compared to existing studies, this system stands out for its accuracy and robustness. It represents an effective tool for detecting drowsiness and reducing vehicle accidents.