Scaling longitudinal functional health assessment in multi-inhabitant smarthome

Abstract

Autonomous longitudinal functional health assessment is critically important to support the rehabilitation of older adults in Skilled Nursing Facilities (SNFs). Although the wide availability of commodity smarthome sensors and internet-of-things (IoT) is facilitating continual monitoring of individuals' health-related vital signs and behaviors, missing values, presence of multi-inhabitants and diversity of smarthomes interfere with successful longitudinal assessment and impact the scalability of autonomous health assessments. In this paper, we propose a novel scalable framework to provide health assessments of older adults living in varied smarthome environments. As a critical first step, we propose a novel algorithm to track individuals in a multi-inhabitant smarthome environment. We then propose a novel data curation technique to address missing sensor signals in a multi-modal ambient sensor-assisted environment. Finally, we propose a novel trajectory featurization method inspired Deep Convolutional Neural Network TDCNN, leveraging appropriate samples from a well-labeled source smarthome, to transfer functional health assessment knowledge to unlabeled diverse smarthomes, boosting the scalability of autonomous health assessment. Our evaluation on real SNFs data, collected over 5 months from 95 individuals residing in 9 diverse sensored SNFs environments shows promising results (93% accuracy) with respect to the scalability of our framework.