WeedGait: Unobtrusive Smartphone Sensing of Marijuana-Induced Gait impairment By Fusing Gait Cycle Segmentation and Neural Networks

Abstract

The use of marijuana is now legal for medical purposes in 39 of the 50 United States. Eleven of these 39 states have also legalized marijuana for non-medical usage. Marijuana impairs the motor skills of users, making Driving Under the Influence of Marijuana (DUIM) a growing public health concern. There are currently few accessible and accurate methods to assess the impairment levels of drivers who have used marijuana. Current assessment methods include self-reports and testing urine, oral fluid, and blood. However, self-reports are often biased and biological tests are cumbersome to perform in situ. In this paper, we investigate whether dose-dependent changes in participants gait (walk) can be detected using data gathered from their smartphone motion sensors (accelerometer and gyroscope). We envision WeedGait, a smartphone sensing system that will assess the gait of marijuana users passively and warn them when they are too impaired to drive safely. To the best of our knowledge, this is the first study on using smartphones to assess marijuana-induced gait impairment. Gait data was collected from 10 subjects and pre-processing steps included low pass filtering, step cycle detection and segmentation, and normalization. We present a novel gait analysis approach that analyzes normalized, single-step segments to achieve higher accuracy than prior approaches. We compared the classification results of various machine and deep learning models, and found that Long Short Time Memory (LSTM) and Support Vector Machines performed best, discriminating the gait of subjects after smoking either marijuana with 3% or 7.2% THC versus smoking a placebo marijuana cigarette with an accuracy of 92.1%. These results suggest that smartphone-based marijuana testing is more accurate than urine-based tests but slightly less accurate than oral fluid based testing. Moreover, smartphone sensing of marijuana is completely passive and hence more convenient, which facilitates pervasive testing in natural settings and could have massive impact due to the near-ubiquity of smartphones.