Research Article
Deriving Relationships between Physiological Change and Activities of Daily Living Using Wearable Sensors
@INPROCEEDINGS{10.1007/978-3-642-23583-2_17, author={Shuai Zhang and Leo Galway and Sally McClean and Bryan Scotney and Dewar Finlay and Chris Nugent}, title={Deriving Relationships between Physiological Change and Activities of Daily Living Using Wearable Sensors}, proceedings={Sensor Systems and Software. Second International ICST Conference, S-Cube 2010, Miami, FL, USA, December 13-15, 2010, Revised Selected Papers}, proceedings_a={S-CUBE}, year={2012}, month={5}, keywords={Wireless Sensors Physiological Profile Activities of Daily Living Health Status Wellbeing}, doi={10.1007/978-3-642-23583-2_17} }- Shuai Zhang
Leo Galway
Sally McClean
Bryan Scotney
Dewar Finlay
Chris Nugent
Year: 2012
Deriving Relationships between Physiological Change and Activities of Daily Living Using Wearable Sensors
S-CUBE
Springer
DOI: 10.1007/978-3-642-23583-2_17
Abstract
The increased prevalence of chronic disease in elderly people is placing requirements for new approaches to support efficient health status monitoring and reporting. Advances in sensor technologies have provided an opportunity to perform continuous point-of-care physiological and activity-related measurement and data capture. Context-aware physiological pattern analysis with regard to activity performance has great potential for health monitoring in addition to the detection of abnormal lifestyle patterns. In this paper, the successful capture of the relationships between physiological and activity profile information is presented. Experiments have been designed to collect ECG data during the completion of five predefined everyday activities using wearable wireless sensors. The impact of these activities on heart rate has been captured through the analysis of changes in heart rate patterns. This has been achieved using CUSUM with change points corresponding to the transition between activities. From this initial analysis a future mechanism for context aware health status monitoring based on sensors is proposed.
