Remote patient monitoring for healthcare has proven to be a valuable resource for continued observation with real-time evaluations, early warnings of the onset of diseases, and possible emergency alerts. Under strict privacy and regulatory constraints, indoor motion sensors overcome the intrusiveness of camera capture as an alternative monitoring method.
This study aims to analyze remote sensor records using machine learning and statistical methods to extract meaningful healthcare insights at individual level patient monitoring. It starts with the hypothesis that with this kind of record for aging patients for example, anomalies to their patterns and behaviours could help identify opportunities for proactive care, including family alerts.
Last updated: April 18, 2018