Evaluating machine learning models to classify occupants' perceptions of their indoor environment and sleep quality from indoor air quality.

A variety of factors can affect a person's perception of their environment and health, but one factor that is often overlooked in indoor settings is the air quality. To address this gap, we develop and evaluate four Machine Learning (ML) models on two disparate datasets using Indoor Air Quality (IAQ) parameters as primary features and components of self-reported IAQ satisfaction and sleep quality as target variables. In each case, we compare models to each other as well as to a simple model that always predicts the majority outcome. In the first analysis, we use open-source data collected from 93 California residences to predict occupant's satisfaction with their indoor environment. Results indicate building ventilation rate, Relative Humidity (RH), and formaldehyde are most influential when predicting IAQ perception and do so with an accuracy greater than the simplified model. The second analysis uses IAQ data gathered from a field study we conducted with 20 participants over 11 weeks to train similar models. We obtain accuracy and F1 scores similar to the simplified model where PM2.5 and TVOCs represent the most important predictors. Our results underscore the ability of IAQ to affect a person's perception of their built environment and health and highlight the utility of ML models to explore the strength of these relationships.Implications: The results from this study show that two outcome variables - occupant's indoor air quality (IAQ) satisfaction and perceived sleep quality - are related to the measured IAQ parameters but not heavily influenced by typical values measured in apartments and homes. This study highlights the ability of machine learning models as exploratory analysis tools to determine underlying relationships within and across datasets in addition to understanding the importance of certain features on the outcome variable. We compare four different models and find that the random forest classifier has the best performance in both analysis on IAQ satisfaction and perceived sleep quality. It is a suitable model for predicting IAQ-related subjective metrics and also provides value insight into the feature importance of the IAQ parameters. The accuracy of any of these machine learning models in predicting occupants' comfort or sleep quality is limited by the dataset size, how data is collected, and range of data. This study identifies the factors that are important to IAQ perception: ventilation rate, relative humidity, and concentrations of formaldehyde, NO2, and particulate matter. It indicates that sensors that can measure these variables are necessary for future, related studies that model occupants' IAQ satisfaction. However, this study does not find strong relationships between any of the IAQ parameters measured in this study and perceived sleep quality despite the logical pathway between these many pollutants and respiratory issues. A prediction model of IAQ perception or sleep quality can be integrated into home management systems to automatically adjust building operations such as ventilation rates in smart buildings. Once buildings are equipped with a network of low-cost sensors that measure concentrations of pollutants and operating conditions of the ventilation system, the prediction model can be used to predict the occupants' comfort and facilitate the control of the ventilation system.

circadian rhythms are not captured equal: Exploring Circadian metrics extracted by differentcomputational methods from smartphone accelerometer and GPS sensors in daily life tracking.

Objective: To identify the differences between circadian rhythm (CR) metrics characterized by different mobile sensors and computational methods. Methods: We used smartphone tracking and daily survey data from 225 college student participants, applied four methods (survey construct automation, cosinor regression, non-parametric method, Fourier analysis) on two types of smartphone sensor data (GPS, accelerometer) to characterize CR. We explored the inter-relations among the extracted circadian metrics as well as between the circadian metrics and participants' self-reported mood and sleep outcomes. Results: Compared to GPS signals, smartphone accelerometer activity follows an intradaily distribution that starts earlier in the day, winds down later, reaches half cumulative activity about the same time, conforms less to a sinusoidal wave, and exhibits more intradaily fragmentation but higher CR strength and lower interdaily disruption. We found a notable negative correlation between intradaily variability and CR strength especially pronounced in GPS activity. Self-reported sleep and mood outcomes showed significant correlations with particular CR metrics. Conclusions: We revealed significant inter-relations and discrepancies in the circadian metrics discovered from two smartphone sensors and four CR algorithms and their bearings on wellbeing indicators such as sleep quality and loneliness.

Exploring Post COVID-19 Outbreak Intradaily Mobility Pattern Change in College Students: A GPS-Focused Smartphone Sensing Study.

With the outbreak of the COVID-19 pandemic in 2020, most colleges and universities move to restrict campus activities, reduce indoor gatherings and move instruction online. These changes required that students adapt and alter their daily routines accordingly. To investigate patterns associated with these behavioral changes, we collected smartphone sensing data using the Beiwe platform from two groups of undergraduate students at a major North American university, one from January to March of 2020 (74 participants), the other from May to August (52 participants), to observe the differences in students' daily life patterns before and after the start of the pandemic. In this paper, we focus on the mobility patterns evidenced by GPS signal tracking from the students' smartphones and report findings using several analytical methods including principal component analysis, circadian rhythm analysis, and predictive modeling of perceived sadness levels using mobility-based digital metrics. Our findings suggest that compared to the pre-COVID group, students in the mid-COVID group generally 1) registered a greater amount of midday movement than movement in the morning (8-10 a.m.) and in the evening (7-9 p.m.), as opposed to the other way around; 2) exhibited significantly less intradaily variability in their daily movement; 3) visited less places and stayed at home more everyday, and; 4) had a significant lower correlation between their mobility patterns and negative mood.

Multi-modal data collection for measuring health, behavior, and living environment of large-scale participant cohorts.

BACKGROUND: As mobile technologies become ever more sensor-rich, portable, and ubiquitous, data captured by smart devices are lending rich insights into users' daily lives with unprecedented comprehensiveness and ecological validity. A number of human-subject studies have been conducted to examine the use of mobile sensing to uncover individual behavioral patterns and health outcomes, yet minimal attention has been placed on measuring living environments together with other human-centered sensing data. Moreover, the participant sample size in most existing studies falls well below a few hundred, leaving questions open about the reliability of findings on the relations between mobile sensing signals and human outcomes. RESULTS: To address these limitations, we developed a home environment sensor kit for continuous indoor air quality tracking and deployed it in conjunction with smartphones, Fitbits, and ecological momentary assessments in a cohort study of up to 1,584 college student participants per data type for 3 weeks. We propose a conceptual framework that systematically organizes human-centric data modalities by their temporal coverage and spatial freedom. Then we report our study procedure, technologies and methods deployed, and descriptive statistics of the collected data that reflect the participants' mood, sleep, behavior, and living environment. CONCLUSIONS: We were able to collect from a large participant cohort satisfactorily complete multi-modal sensing and survey data in terms of both data continuity and participant adherence. Our novel data and conceptual development provide important guidance for data collection and hypothesis generation in future human-centered sensing studies.