User‐Centric Indoor Air‐Quality Monitoring on Mobile Devices

Abstract

Since people spend a majority of their time indoors, indoor air quality (IAQ) can have a significant impact on human health, safety, productivity, and comfort. Due to the diversity and dynamics of people's indoor activities, it is important to monitor IAQ for each individual. Most existing air quality sensing systems are stationary or focus on outdoor air quality. In contrast, we propose MAQS, a user-centric mobile sensing system for IAQ monitoring. MAQS users carry portable, indoor location tracking and IAQ sensing devices that provide personalized IAQ information in real time. To improve accuracy and energy efficiency, MAQS incorporates three novel techniques: (1) an accurate temporal n-gram augmented Bayesian room localization method that requires few Wi-Fi fingerprints; (2) an air exchange rate based IAQ sensing method, which measures general IAQ using only CO$_2$ sensors; and (3) a zone-based proximity detection method for collaborative sensing, which saves energy and enables data sharing among users. MAQS has been deployed and evaluated via a real-world user study. This evaluation demonstrates that MAQS supports accurate personalized IAQ monitoring and quantitative analysis with high energy efficiency. We also found that study participants frequently experienced poor IAQ.

Personal pollution monitoring: mobile real-time air quality in daily life

“…The InAir [13] and MAQS [11] systems target the significant challenge of indoor air quality sensing, an important area since, as reported by Jiang et al, on average over 90% of modern life is lived indoors [11]. InAir provided participants with a stationary indoor air quality sensor for particulate matter.…”

“…The MAQS [11] air quality system also explored improving indoor air tracking through mobile sensors that sampled CO2 and interpolated VOCs (volatile organic compounds) using air exchange rates. The focus was to give personalized, room-level data to individuals that used the system.…”

Air quality monitoring and management system model of vehicles based on the internet of things

“…This work aimed to provide pollution statistics to government officials, organizations, and individuals to solve their specific problems and requirements [4]. Jiang et al in 2011, reported a personalized mobile sensing system for indoor air quality checks using smartphones, data, and web servers [5]. In 2012, Hasenfratz et al reported a mobile sensing system for participatory air quality monitors with low cost and low power using ozone sensor MiCS-OZ-47 [6].…”

Optimal resource usage in ultra-low-power sensor interfaces through context- and resource-cost-aware machine learning

“…But for a cell phone this e.g. can be achieved by combining observed cellular IDs and inertial sensors [27]. We suspect that changes in context only happen at worst once a minute.…”