A system for objectively measuring behavior and the environment to support large-scale studies on childhood obesity

TL;DR

This paper introduces BigO, an integrated system for passive, smartphone- and wearable-based measurement of child behavior and environmental factors to support large-scale obesity studies. It defines a three-layer architecture and privacy-preserving geospatial aggregation to derive population-level indicators from high-rate sensor data and public environmental datasets. The authors validate core indicators on public datasets (e.g., step counts with around $8$ steps absolute error and visited-location F1 near $0.86$) and demonstrate real-world deployments in schools and clinics, illustrating policy and clinical utility. They discuss design, processing pipelines, and scalable implementation choices (edge processing, Cassandra/Spark) and outline implications for public health decision-making and official statistics.

Abstract

Advances in IoT technologies combined with new algorithms have enabled the collection and processing of high-rate multi-source data streams that quantify human behavior in a fine-grained level and can lead to deeper insights on individual behaviors as well as on the interplay between behaviors and the environment. In this paper, we present an integrated system that collects and extracts multiple behavioral and environmental indicators, aiming at improving public health policies for tackling obesity. Data collection takes place using passive methods based on smartphone and smartwatch applications that require minimal interaction with the user. Our goal is to present a detailed account of the design principles, the implementation processes, and the evaluation of integrated algorithms, especially given the challenges we faced, in particular (a) integrating multiple technologies, algorithms, and components under a single, unified system, and (b) large scale (big data) requirements. We also present evaluation results of the algorithms on datasets (public for most cases) such as an absolute error of 8-9 steps when counting steps, 0.86 F1-score for detecting visited locations, and an error of less than 12 mins for gross sleep time. Finally, we also briefly present studies that have been materialized using our system, thus demonstrating its potential value to public authorities and individual researchers.

Figures (4)

• Figure 1: Generic architecture of the proposed system
• Figure 2: Data aggregation: from raw data to population-level behavioral indicators
• Figure 3: UML Component diagram of the proposed system architecture.
• Figure 4: Point-of-interest detection example with development data. Map data from Open Street Map.