Leveraging Ubiquitous Sensing for Quantifying the Quality of Motion in Mobile Health

Ubiquitous sensing from smartphones and wearable devices have proven to be useful for a variety of applications, from sports to modern medicine. These devices are embedded with powerful sensors which track the motion of an object in real time. From this data, quantitative measures of motion can be extracted while also assessing the quality of that movement.
Motor function assessments are designed to evaluate human performance, but the outcome measures of these assessments are often based on subjective or ordinal rating scales that do not keep track of motion quantitatively. In this dissertation, we leverage ubiquitous sensing and signal-based curve matching to quantify the quality of motion through the development of an objective scoring measure . We then validate our measure with a novel study involving the functional assessment of patients with neuromuscular disorders.
We also demonstrate the feasibility of ubiquitous sensing combined with signal feature analysis to detect and assess rehabilitation progress in patients post-ACL reconstruction surgery. Finally, we present a visualization framework that combines analytical modeling with comparative trajectory analysis to model motion data into meaningful information related to the quantity and quality of motion.