Drowsiness Monitoring with EEG-Based MEMS Biosensing Technologies

Abstract

Electroencephalography (EEG) has been widely adopted to monitor changes in cognitive states, particularly stages of sleep, as EEG recordings contain a wealth of information reflecting changes in alertness and sleepiness. In this study, silicon dry electrodes based on Micro-Electro-Mechanical Systems (MEMS) were developed to bring high-quality EEG acquisition to operational workplaces. They have superior conductivity performance, large signal intensity, and are smaller in size than conventional (wet) electrodes. An EEG-based drowsiness estimation system consisting of a dry-electrode array, power spectrum estimation, principal component analysis (PCA)-based EEG signal analysis, and multivariate linear regression was developed to estimate drivers’ drowsiness levels in a virtual-reality-based dynamic driving simulator. The proposed system can help elders who are often affected by periods of tiredness and fatigue.