Dynamic classification of personal microenvironments using a suite of wearable, low-cost sensors

Abstract

Human exposure to air pollution is associated with increased risk of morbidity and mortality. However, personal air pollution exposures can vary substantially depending on an individual’s daily activity patterns and air quality within their residence and workplace. To develop and validate an adaptive buffer size (ABS) algorithm capable of dynamically classifying an individual’s time spent in predefined microenvironments using data from global positioning systems (GPS), motion sensors, temperature sensors, and light sensors. Twenty-two participants in Fort Collins, CO were recruited to carry a personal air sampler for a 48-hour period. The personal sampler was retrofitted with a GPS and a pushbutton to complement the existing sensor measurements (temperature, motion, light). The pushbutton was used in conjunction with a traditional time-activity diary to note when the participant was located at “home”, “work”, or within an “other” microenvironment. The ABS algorithm predicted the amount of time spent in each microenvironment with a median accuracy of 99.1%, 98.9%, and 97.5% for the “home”, “work”, and “other” microenvironments. The ability to classify microenvironments dynamically in real-time can enable the development of new sampling and measurement technologies that classify personal exposure by microenvironment.

Quantitative Self-Assessment of Exposure to Solvents among Formal and Informal Nail Technicians in Johannesburg, South Africa

“…In our study, we used a cutoff for a sampling duration of three hours, but the results might still be inaccurate. Future SAE and citizen science studies will benefit from the further development of various wearable low-cost sensors that provide not only estimates of pollutants’ concentrations, but also complementary information to evaluate the results from the perspective of exposure assessment [ 24 ].…”

Automated classification of time-activity-location patterns for improved estimation of personal exposure to air pollution

“…Time-activity patterns and modes of transport cannot be derived from the GPS raw data directly without further data processing. Only a few studies aim to classify time-activity patterns during daily life using GPS tracking data (smartphone-based or handheld devices), in some cases combined with temperature, light or motion sensors [17,18,19,20,21,22,23,24] to develop primarily rule-based models and/or random forest (RF) learning techniques for a small number of participants over a few days.…”

“…If a single cluster was identified, a spatial elliptical zone ("buffer zone") was created around each home microenvironment by extracting the centroid coordinates and the individual spread distances (δLon and δLat) (Figure 2c). Any spread is expected to depend on contextual factors (such as building construction characteristics and GPS signal quality) and was typically found to range from 60m to 500m( [23,24]. Data points within that spatial zone (Figure 2c) were classified as home and were separated into indoor and outdoor in Step 4.…”

Public engagement with air quality data: using health behaviour change theory to support exposure-minimising behaviours

“…Recent advances in sensor technology have resulted in lower cost sensors of variable quality [12] supplementing the static infrastructure in many contexts and, in some cases, is the only viable monitoring option owing to economic, infrastructural, or political factors [13,14]. While these sensors may be used to monitor air quality in outdoor or indoor contexts, many can also be used to monitor personal exposure by an individual wearing a sensor [15,16]. A person's exposure to air pollution will be unique to them and depends on numerous factors including their geographic location, time-activity patterns, occupation, gender and socio-economic status [17].…”