Usability of Smart Home Thermostat to Evaluate the Impact of Weekdays and Seasons on Sleep Patterns and Indoor Stay: Observational Study

Abstract

Background Sleep behavior and time spent at home are important determinants of human health. Research on sleep patterns has traditionally relied on self-reported data. Not only does this methodology suffer from bias but the population-level data collection is also time-consuming. Advances in smart home technology and the Internet of Things have the potential to overcome these challenges in behavioral monitoring. Objective The objective of this study is to demonstrate the use of smart home thermostat data to evaluate household sleep patterns and the time spent at home and how these behaviors are influenced by different weekdays and seasonal variations. Methods From the 2018 ecobee Donate your Data data set, 481 North American households were selected based on having at least 300 days of data available, equipped with ≥6 sensors, and having a maximum of 4 occupants. Daily sleep cycles were identified based on sensor activation and used to quantify sleep time, wake-up time, sleep duration, and time spent at home. Each household’s record was divided into different subsets based on seasonal, weekday, and seasonal weekday scales. Results Our results demonstrate that sleep parameters (sleep time, wake-up time, and sleep duration) were significantly influenced by the weekdays. The sleep time on Fridays and Saturdays is greater than that on Mondays, Wednesdays, and Thursdays (n=450; P<.001; odds ratio [OR] 1.8, 95% CI 1.5-3). There is significant sleep duration difference between Fridays and Saturdays and the rest of the week (n=450; P<.001; OR 1.8, 95% CI 1.4-2). Consequently, the wake-up time is significantly changing between weekends and weekdays (n=450; P<.001; OR 5.6, 95% CI 4.3-6.3). The results also indicate that households spent more time at home on Sundays than on the other weekdays (n=445; P<.001; OR 2.06, 95% CI 1.64-2.5). Although no significant association is found between sleep parameters and seasonal variation, the time spent at home in the winter is significantly greater than that in summer (n=455; P<.001; OR 1.6, 95% CI 1.3-2.3). These results are in accordance with existing literature. Conclusions This is the first study to use smart home thermostat data to monitor sleep parameters and time spent at home and their dependence on weekday, seasonal, and seasonal weekday variations at the population level. These results provide evidence of the potential of using Internet of Things data to help public health officials understand variations in sleep indicators caused by global events (eg, pandemics and climate change).

Revealing the Mysteries of Population Mobility Amid the COVID-19 Pandemic in Canada: Comparative Analysis With Internet of Things–Based Thermostat Data and Google Mobility Insights

“…These 4 provinces constitute approximately 87% of the Canadian population [ 21 ]. The reliability and validity of the ecobee data set were rigorously assessed in our prior studies, as detailed in our previously published research [ 20 , 22 , 23 ]. Information regarding Canadian policy implementation dates across provinces was obtained from a dedicated platform managed by the Canadian Government to share COVID-19–related information regularly [ 24 ].…”

“…ecobee’s data were transferred from Google’s BigQuery to the Microsoft Azure cloud services platform [ 25 ]. Data were prepared using Azure Databricks data analytics platform and Jupyter Notebook (Jupyter Team) using Python; detailed explanation of the whole process has been mentioned in our previous studies [ 20 , 23 ]. Data cleaning, analysis, and visualization were done in R studio (version 1.4.1106; Posit Software, PBC) with R software (version 4.0.5; The R Foundation) and data analysis packages tidyverse [ 26 ] and timetk [ 27 ].…”

Planetary sleep medicine: Studying sleep at the individual, population, and planetary level

“…Moreover, the utilization of digital health devices and the “Internet of Things” (IoT), such as smartphone apps and smart home thermostats, could be leveraged to pave the way for a “digital planetary sleep medicine” ( 107 ). However, IoT may work only in middle- and high-income countries.…”