Standalone Wearable Driver Drowsiness Detection System in a Smartwatch

摘要: Drowsiness while driving is one of the main causes fatal accidents, especially on monotonous routes such as highways. The goal this paper to design a completely standalone, distraction-free, and wearable system for driver drowsiness detection by incorporating in smartwatch. objective detect driver’s level based behavior derived from motion data collected built-in sensors smartwatch, accelerometer gyroscope. For purpose, magnitudes hand movements are extracted used calculate time, spectral, phase domain features. features selected feature correlation method. Eight serve an input support vector machine (SVM) classifier. After SVM training testing, highest obtained accuracy was 98.15% (Karolinska sleepiness scale). This user-predefined can be both left-handed right-handed users, because different models hands. effective, safe, distraction-free drowsiness.