Standalone Wearable Driver Drowsiness Detection System in a Smartwatch

Abstract

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

Assessment of the Potential of Wrist-Worn Wearable Sensors for Driver Drowsiness Detection

“…In contrast to the device used in this work, these devices are not yet ready for the market, which makes a future and large-scale use in the vehicle difficult. The use of motion sensors in the wearables to evaluate the steering behavior will be more difficult in the future [66,67], since the degree of automation will steadily increase. By using physiological data from wearables, as in the previous case as the sole data source that is continuously measured, this problem no longer exists.…”

“…Lee et al utilized the built-in motion sensors of a smartwatch for driver drowsiness detection by evaluating the driving behavior [66]. Twenty subjects participated in a simulator study.…”

“…When available on the market, they were combined with another or more intrusive measurement [47,70]. Focusing on future automated driving, sensors like accelerometer or gyroscope will be more difficult or in a different way to use since movement patterns from the steering cannot be continuously evaluated for driver state detection [66,67]. In view of this, the aim of this work was to investigate and assess the potential and feasibility of using physiological data (HRV) from a wrist-worn wearable device, readily available on the consumer electronics market, as single data source in combination with a common machine learning model for driver drowsiness detection.…”

Non-intrusive Driver Drowsiness Detection based on Face and Eye Tracking

“…A contrast to SSS, this scale is considered a robust scale capable of categorizing driver's drowsiness into different levels [46]. Authors in [14] and [18] used KSS to define five, and three drowsiness states of their systems respectively. Also, a review of literature relating to DDD by [5] indicates KSS is the most preferred scale of these two scales.…”

“…This tracking was done on a video dataset containing almost 2 hours of driver drowsiness states occurring during the day and night. The night data were very crucial in generalizing the accuracy of the machine learning models as drowsiness is predicted to occur mostly at night [18,19]. Once the eye states were captured, they were passed to the machine learning models for classification.…”