Abstract
As one of the biggest contributors to road accidents and fatalities, drink driving is worthy of significant research attention. However, most existing systems on detecting or preventing drink driving either require special hardware or require much effort from the user, making these systems inapplicable to continuous drink driving monitoring in a real driving environment. In this paper, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DetectDUI</i> , a contactless, non-invasive, real-time system that yields a relatively highly accurate drink driving monitoring by combining vital signs (heart rate and respiration rate) extracted from in-car WiFi system and driver’s psychomotor coordination through steering wheel operations. The framework consists of a series of signal processing algorithms for extracting clean and informative vital signs and psychomotor coordination, and integrate the two data streams using a self-attention convolutional neural network (i.e., C-Attention). In safe laboratory experiments with 15 participants, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DetectDUI</i> achieves drink driving detection accuracy of 96.6% and BAC predictions with an average mean error of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2\sim 5mg/dl$ </tex-math></inline-formula> . These promising results provide a highly encouraging case for continued development.
Highlights
I N 2018, The US suffered 10, 511 deaths from drunkdriving crashes [1]
We propose a novel adaptive variational mode decomposition (AVMD) method to separate the mixed signal into multiple modes, and keep the modes that relate to breathing and heartbeat respectively
The signals of breathing and heartbeat are extracted from WiFi signals and the psychomotor coordination is monitored by the in-car inertial measurement unit (IMU) [8] including the gyroscope and the acceleration signals
Summary
I N 2018, The US suffered 10, 511 deaths from drunkdriving crashes [1]. The WHO reports that, in high-income countries, as many as 20% of fatally injured drivers have excess alcohol in their blood. COVID-related deaths may dwarf these numbers, but it is important not to lose our prepandemic perspective. DetectDUI measures a person’s vital signs through WiFi signals and their psychomotor coordination through steering wheel operations. We remove sudden changes and preserve only signals during relatively stable driving periods, which show a clear cyclic pattern that corresponds to breathing cycles, but the heartbeat pattern is drowned due to its much weaker amplitude To address this problem, we propose a novel adaptive variational mode decomposition (AVMD) method to separate the mixed signal into multiple modes, and keep the modes that relate to breathing and heartbeat respectively. We use IMU to record the acceleration and gyroscope data during operation In this way, we obtain a continuous monitoring of psychomotor coordination of the driver without interfering with their driving.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
