Drunk Driving Detection System Using Wearable Devices

Seunghwa Lee, Joon Yoo

http://doi.org/10.5626/JOK.2022.49.5.397

Drunk driving may cause traffic accidents that result in human casualties. Even though most people are well aware of the danger, many traffic accidents still occur due to poor judgement caused by drinking. In this paper, we propose a drunk driving detection system using wearable devices. First, we use a smart watch, a wearable device, to collect data using only general-purpose sensors and sends the data via a smart phone to a server that performs machine learning to determine if the user is drinking. Then, the driver detection algorithm, which uses in-car beacons, sends a warning to the user to prevent drunk driving. We implemented the system on a smart watch, smart phone, and server, and also developed a practical user mobile app. The results showed that the accuracy of drinking detection and driver detection algorithms were around 92% and 99%, respectively.