Accepted for/Published in: JMIR mHealth and uHealth
Date Submitted: Jun 8, 2020
Open Peer Review Period: Jun 16, 2020 - Jun 29, 2020
Date Accepted: Oct 24, 2020
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Understanding user behaviour through the use of unsupervised anomaly detection: Using IoT smart home thermostat data
ABSTRACT
Background:
Background:
One of the main concerns of public health surveillance is to preserve the physical and mental health of older adults while supporting their independence and privacy. On the other hand, to better assist those individuals with essential healthcare services in the event of an emergency, their regular activities should be monitored. To this end, the Internet of Things (IoT) is employed to track the sequence of activities of individuals via ambient sensors and to collect data such as daily activity patterns. Previous surveys to identify the regular activity patterns of older adults were deficient in the limited number of participants, tracking the activities for a short period of time, and highly reliant on predefined normal activity.
Objective:
Objective:
The objective of this study is to overcome the aforementioned challenges by utilizing large-scale data from smart home thermostats that collect the motion status of individuals for every 5-minute interval over a long period of time.
Methods:
Methods:
We used the data from smart home thermostats for a sample of 30 households. The indoor activity patterns are captured through motion sensors. We used the unsupervised time-based, deep, neural-network architecture (Long Short Term Memory-Variational Autoencoder) LSTM-VAE to identify regular activity patterns for each household for two scales of time: annual and weekday.
Results:
Results:
The utilization of this approach has enabled us to detect the anomalous days, as the rare activity patterns that differ from the regular activity model. In addition to the anomaly detection, other indoor behaviours are measured by the regular activity model such as sleeping time, wake up time, time spent indoors.
Conclusions:
Conclusions:
The leverage of this approach could enhance individual health monitoring as well as public health surveillance. As it provides a non-adhesive surveillance tool to assist public level officials and governments in policy development and emergency personnel in the event of an emergency by measuring indoor behaviour while preserving privacy and using existing commercially available thermostat equipment.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.