Proteus: Towards a Manageability-focused Home-based Health Monitoring Infrastructure

A data collection infrastructure is vital for generating sufficient amounts and diversity of data necessary for developing algorithms in home-based health monitoring. However, the manageability - -deployment and operation efforts - -of such an infrastructure has long been overlooked. Even a small size of a dozen homes may incur enormous manual efforts on the research team, including installing, configuring and updating of sensor, edge devices; continuous monitoring for faults and errors to prevent data losses, and integrating new sensing modalities. In this paper, we present Proteus, an easily managed infrastructure designed to automate much of the work in deploying and operating such systems. Proteus includes: i) scalable, continuous deployment and update of devices with automatic bootstrapping; ii) automatic fault and error monitoring and recovery with watchdogs and LED feedback, and complementary edge and cloud storage backups; and iii) an easy-to-use data-agnostic pipeline for integrating new modalities. We demonstrate our system's robustness through different sets of experiments: 3 sensor nodes running for 24 days sending data (17.3 Mbps aggregate rate), and 16 emulated sensors (92.8 Mbps aggregate rate). All such experiments have data loss rates less than 1%. Further we reduce human efforts by 25-fold and code required for adding new data modality by 25-fold. Our results show that Proteus is a promising solution for enabling research teams to effectively manage home-based health monitoring at small to medium sizes.