Smartwatch-based driver alertness monitoring with wearable motion and physiological sensor

Abstract

Studies have shown that a high precision driver alertness monitoring system is an essential and a monetary countermeasure to reduce the road accidents. This paper presents a novel approach to measure the driver alertness, evaluated by a smartwatch device based on fusion of direct and indirect method. The driver chronic physiological state is monitor by adopting a photoplethysmography sensor on the driver finger that is connected to a wrist-type wearable device. A Bluetooth Low Energy module connected to the wearable device transmits the PPG data to the smartwatch in real-time. Meanwhile, the indirect method, driver steering wheel movement can be derived by utilizing the motion sensors integrated in the smartwatch which include a tri-axis accelerometer and a gyroscope sensors. The respiration signals can be derived from the PPG time- and frequency-domains attributes. The data obtained from both methods aforementioned are subsequently decomposed into relevant features in time, spectral context and phase space domain, and thus computes the alertness index. Here, the correlations between the extracted features and the subjective Koralinska Sleepiness Scale are studied as well along with the recorded experimental videos. This study reveals that the alertness index prediction accuracy can be reached up to 96.3% based on the descriptive extracted features.

Detecting driver fatigue using heart rate variability: A systematic review

“…(Jung et al, 2014) used integrated ECG electrodes on the steering wheel. Photoplethysmography (PPG) based solutions can be even easier to use since they can be integrated in wrist bands (Kundinger et al, 2020a(Kundinger et al, , 2020bLee et al, 2015) or the steering wheel (Rahim et al, 2015). This advantage may enable pervasive usage in daily driving scenarios for HRV based monitoring.…”

dWatch

“…In the driving environment, the detection of a relative movement between the vehicle and the driver's hand can be used to indicate that the driver's hand may be operating the steering wheel. We leverage the work from Bi et al [5] to detect if the driver's hand is moving by comparing the acceleration of the smart watch ( a w ) and the acceleration of the smart phone (| a p |) [20]. Since the coordinates of the smart phone and the smart watch are not aligned, the components of the acceleration of the two devices in various directions cannot be directly compared.…”

“…The average number of adjustments during waking is 26 per minute, while the average number of adjustments during slumber is only 9 per minute [22]. For the steering angle, θ is focused at |θ | ≤ 90 • since the drowsiness-induced SWM factor is bounded at no more than 10 o angle according to current research [20]. Thus, driver drowsiness detection can be done by monitoring the number of steering wheel adjustments by hand and the steering angle.…”

“…Considering the advantages and disadvantages of various methods, researchers usually combine two or more methods to driver's drowsiness. Lee et al [20] detect driver alertness by wearable motion and physiological sensors and achieves an accuracy of over 96%. This work requires a PPG sensor connected to a wrist-wearable device to collect a PPG signal from the driver's finger.…”

SafeWatch

“…Recently, the emerging Internet of Things (IoT) systems for smart driving provide a promising solution. Several methods have been developed to detect the driver's dangerous actions [21] [20] [23] [24] [25]. However, these designs require additional devices such as cameras, PPG sensors or pressure sensors, presenting the barrier to wide adoption.…”