Search Results

Abstract: Drowsiness detection is a crucial aspect of preventing accidents in various domains, including transportation, healthcare, and workplace safety. Electroencephalography (EEG) signals provide an effective means of detecting drowsiness due to their ability to capture brainwave activity in real-time. However, the complexity of EEG data and the need for accurate classification necessitate robust machine learning techniques. This paper presents an efficient Support Vector Machine (SVM)-based learning approach for drowsiness detection using EEG signals. The proposed method employs feature extraction techniques, dimensionality reduction, and optimized kernel functions to enhance classification accuracy while maintaining computational efficiency. Experimental results demonstrate that SVM outperforms traditional machine learning classifiers, achieving high detection accuracy with low false positive rates, making it a viable solution for real-time drowsiness monitoring systems.