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

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.

[1]  Emmanuel Agu,et al.  Investigating postural sway features, normalization and personalization in detecting blood alcohol levels of smartphone users , 2016, 2016 IEEE Wireless Health (WH).

[2]  J. F. Yang,et al.  Electromyographic amplitude normalization methods: improving their sensitivity as diagnostic tools in gait analysis. , 1984, Archives of physical medicine and rehabilitation.

[3]  Jeffrey M. Hausdorff,et al.  Altered fractal dynamics of gait: reduced stride-interval correlations with aging and Huntington's disease. , 1997, Journal of applied physiology.

[4]  Lior Rokach,et al.  Virtual Breathalyzer: Towards the Detection of Intoxication Using Motion Sensors of Commercial Wearable Devices , 2016, Sensors.

[5]  Sudeep Sarkar,et al.  Improved gait recognition by gait dynamics normalization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Owen Carmichael,et al.  Examining Relationships between Multiple Self-Reported Sleep Measures and Gait Domains in Cognitively Healthy Older Adults , 2019, Gerontology.

[7]  G. Shan,et al.  Non-motor predictors of freezing of gait in Parkinson's disease. , 2019, Gait & posture.

[8]  Anup Nandy,et al.  Statistical methods for analysis of Parkinson’s disease gait pattern and classification , 2019, Multimedia Tools and Applications.

[9]  Begonya Garcia-Zapirain,et al.  Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications , 2014, Sensors.

[10]  Hassan Ghasemzadeh,et al.  CyclePro: A Robust Framework for Domain-Agnostic Gait Cycle Detection , 2019, IEEE Sensors Journal.

[11]  Zhelong Wang,et al.  Body Sensor Network-Based Gait Quality Assessment for Clinical Decision-Support via Multi-Sensor Fusion , 2019, IEEE Access.

[12]  James Poling,et al.  The effect of cannabis compared with alcohol on driving. , 2009, The American journal on addictions.

[13]  E. Cone,et al.  Detection of marijuana use by oral fluid and urine analysis following single-dose administration of smoked and oral marijuana. , 2001, Journal of analytical toxicology.

[14]  Hua Fang,et al.  iMStrong: Deployment of a Biosensor System to Detect Cocaine Use , 2015, Journal of Medical Systems.