Estimation of Blood Alcohol Concentration From Smartphone Gait Data Using Neural Networks

Driving is a dynamic activity, which requires quick reflexes and decision making in order to respond to sudden changes in traffic conditions. Alcohol consumption impairs motor and cognitive skills, and causes many driving-related accidents annually. Passive methods of proactively detecting drivers who are too drunk to drive in order to notify them and prevent accidents, have recently been proposed. The effects of alcohol on a drinker’s gait (walk) is a reliable indicator of their intoxication level. In this paper, we investigate detecting drinkers’ intoxication levels from their gait by using neural networks to analyze sensor data gathered from their smartphone. Using data gathered from a large controlled alcohol study, we perform regression analysis using a Bi-directional Long Short Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN) architectures to predict a person’s Blood Alcohol Concentration (BAC) from their smartphone’s accelerometer and gyroscope data. We innovatively proposed a comprehensive suite of pre-processing techniques and model-specific extensions to vanilla CNN and bi-LSTM models, which are well thought out and adapted specifically for BAC estimation. Our Bi-LSTM architecture achieves an RMSE of 0.0167 and the CNN architecture achieves an RMSE of 0.0168, outperforming state-of-the-art intoxication detection models using Bayesian Regularized Multilayer Perceptrons (MLP) (RMSE of 0.017) and the Random Forest (RF), with hand-crafted features. Moreover, our models learn features from raw sensor data, obviating the need for hand-crafted features, which is time consuming. Moreover, they achieve lower variance across folds and are hence more generalizable.

[1]  Steven D. Levitt,et al.  Estimating the Effect of Alcohol on Driver Risk Using Only Fatal Accident Statistics , 1999 .

[2]  Yu Zhao,et al.  Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors , 2017, Mathematical Problems in Engineering.

[3]  Carlo Luschi,et al.  Revisiting Small Batch Training for Deep Neural Networks , 2018, ArXiv.

[4]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  Emmanuel Agu,et al.  Smartphone Inference of Alcohol Consumption Levels from Gait , 2015, 2015 International Conference on Healthcare Informatics.

[7]  Wojciech Zaremba,et al.  Recurrent Neural Network Regularization , 2014, ArXiv.

[8]  Yoshua Bengio,et al.  Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition , 2017, INTERSPEECH.

[9]  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).

[10]  Baoqi Huang,et al.  A Novel Walking Detection and Step Counting Algorithm Using Unconstrained Smartphones , 2018, Sensors.

[11]  Geoffrey E. Hinton,et al.  Layer Normalization , 2016, ArXiv.

[12]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[13]  Shaohan Hu,et al.  DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing , 2016, WWW.

[14]  J. Desmond,et al.  Alcohol and the Cerebellum: Effects on Balance, Motor Coordination, and Cognition. , 1995 .

[15]  Ruslan Salakhutdinov,et al.  Action Recognition using Visual Attention , 2015, NIPS 2015.

[16]  G. Fein,et al.  Impairment on a simulated gambling task in long-term abstinent alcoholics. , 2004, Alcoholism, clinical and experimental research.

[17]  Thomas Plötz,et al.  Ensembles of Deep LSTM Learners for Activity Recognition using Wearables , 2017, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[18]  Qian Wang,et al.  Deep Learning-Based Gait Recognition Using Smartphones in the Wild , 2018, IEEE Transactions on Information Forensics and Security.

[19]  B. Kapur,et al.  Calculation of blood alcohol concentration (BAC) by sex, weight, number of drinks and time. , 1987, Canadian journal of public health = Revue canadienne de sante publique.

[20]  Kaveh Pahlavan,et al.  Smartphone-based gait assessment to infer Parkinson's disease severity using crowdsourced data , 2017, 2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT).

[21]  Mikkel Baun Kjærgaard,et al.  Smart Devices are Different: Assessing and MitigatingMobile Sensing Heterogeneities for Activity Recognition , 2015, SenSys.

[22]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[23]  Tim Oates,et al.  Imaging Time-Series to Improve Classification and Imputation , 2015, IJCAI.

[24]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

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

[26]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[27]  Tim Oates,et al.  Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks , 2014 .

[28]  Shih-Chii Liu,et al.  Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences , 2016, NIPS.

[29]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Hassan A. Karimi,et al.  An Artificial Neural Network for Movement Pattern Analysis to Estimate Blood Alcohol Content Level , 2017, Sensors.

[32]  John D. Lee,et al.  Assessing the Feasibility of Vehicle-Based Sensors to Detect Alcohol Impairment , 2010 .

[33]  Xingjian Zhang,et al.  Study of the Effects of Alcohol on Drivers and Driving Performance on Straight Road , 2014 .

[34]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[35]  Stefan Rust,et al.  A method to align the coordinate system of accelerometers to the axes of a human body: The depitch algorithm , 2012, Comput. Methods Programs Biomed..

[36]  Zhiwen Yu,et al.  Behavioral Biometrics for Continuous Authentication in the Internet-of-Things Era: An Artificial Intelligence Perspective , 2020, IEEE Internet of Things Journal.

[37]  Xiaogang Wang,et al.  Residual Attention Network for Image Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.