​

 

Abstract

Driving under the influence of alcohol is a widespread phenomenon in the US where it is considered a major cause of fatal accidents. In this research we present a novel approach and concept for detecting intoxication from motion differences obtained by the sensors of wearable devices. We formalize the problem of drunkenness detection as a supervised machine learning task, both as a binary classification problem (drunk or sober) and a regression problem (the breath alcohol content level). 
In order to test our approach, we collected data from 30 different subjects (patrons at three bars) using Google Glass and the LG G-watch, Microsoft Band, and Samsung Galaxy S4. We validated our results against an admissible breathalyzer used by the police. 
A system based on this concept, successfully detected intoxication and achieved the following results: 0.95 AUC and 0.05 FPR, given a fixed TPR of 1.0. Applications based on our system can be used to analyze the free gait of drinkers when they walk from the car to the bar and vice-versa, in order to alert people, or even a connected car and prevent people from driving under the influence of alcohol.

 

Citation

@article{DBLP:journals/corr/NassiRE16,

author = {Ben Nassi and Lior Rokach and Yuval Elovici},

title = {Virtual Breathalyzer},

journal = {CoRR}, volume = {abs/1612.05083}, year = {2016},

url = {http://arxiv.org/abs/1612.05083},

archivePrefix = {arXiv}, eprint = {1612.05083}, timestamp = {Mon, 13 Aug 2018 16:48:09 +0200},

biburl = {https://dblp.org/rec/bib/journals/corr/NassiRE16},

bibsource = {dblp computer science bibliography, https://dblp.org} }

​