HAWAD: Hand Washing Detection using Wrist Wearable Inertial Sensors

Hand hygiene is crucial in preventing the spread of infections and diseases. Lack of hand hygiene is one of the major reasons for healthcare associated infections (HAIs) in hospitals. Adherence to hand hygiene compliance by the workers in the food business is very important for preventing food-borne illness. In addition to healthcare settings and food businesses, hand washing is also vital for personal well-being. Despite the importance of hand hygiene, people often do not wash hands when necessary. Automatic detection of hand washing activity can facilitate just-in-time alerts when a person forgets to wash hands. Monitoring hand washing practices is also essential in ensuring accountability and providing personalized feedback, particularly in hospitals and food businesses. Inertial sensors available in smart wrist devices can capture hand movements, and so it is feasible to detect hand washing using these devices. However, it is challenging to detect hand washing using wrist wearable sensors since hand movements are associated with a wide range of activities. In this paper, we present HAWAD, a robust solution for hand washing detection using wrist wearable inertial sensors. We leverage the distribution of penultimate layer output of a neural network to detect hand washing from a wide range of activities. Our method reduces false positives by 77% and improves F1-score by 30% compared to the baseline method.

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

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

[3]  Saiful Islam,et al.  Mahalanobis Distance , 2009, Encyclopedia of Biometrics.

[4]  John A. Stankovic,et al.  Harmony: A Hand Wash Monitoring and Reminder System using Smart Watches , 2015, EAI Endorsed Trans. Ambient Syst..

[5]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[6]  Ted Herman,et al.  Hand hygiene duration and technique recognition using wrist-worn sensors , 2015, IPSN.

[7]  Kibok Lee,et al.  A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks , 2018, NeurIPS.

[8]  B. Allegranzi,et al.  The World Health Organization Guidelines on Hand Hygiene in Health Care and Their Consensus Recommendations , 2009, Infection Control & Hospital Epidemiology.

[9]  Thomas Plötz,et al.  Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables , 2016, IJCAI.

[10]  M. Ross.  Evaluation of Risks Related to Microbiological Contamination of Ready-to-eat Food by Food Preparation Workers and the Effectiveness of Interventions to Minimize Those Risks , 2005 .

[11]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[12]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[13]  Thaier Hayajneh,et al.  Smartphone and Smartwatch-Based Biometrics Using Activities of Daily Living , 2019, IEEE Access.

[14]  Nicholas D. Lane,et al.  Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables , 2016, SenSys.

[15]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[16]  Gregory D. Abowd,et al.  Wristwash: towards automatic handwashing assessment using a wrist-worn device , 2018, UbiComp.

[17]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[18]  Hugo Sax,et al.  Evidence-based model for hand transmission during patient care and the role of improved practices. , 2006, The Lancet. Infectious diseases.

[19]  B. Allegranzi,et al.  Role of hand hygiene in healthcare-associated infection prevention. , 2009, The Journal of hospital infection.