Use this URL to cite or link to this record in EThOS:
Title: A pervasive body sensor network for monitoring post-operative recovery
Author: Aziz, Omer
ISNI:       0000 0001 3870 5194
Awarding Body: Imperial College London
Current Institution: Imperial College London
Date of Award: 2010
Availability of Full Text:
Access from EThOS:
Access from Institution:
Over the past decade, miniaturisation and cost reduction brought about by the semiconductor industry has led to computers smaller in size than a pin head, powerful enough to carry out the processing required, and affordable enough to be disposable. Similar technological advances in wireless communication, sensor design, and energy storage have resulted in the development of wireless "Body Sensor Network (BSN) platforms comprising of tiny integrated micro sensors with onboard processing and wireless data transfer capability, offering the prospect of pervasive and continuous home health monitoring. In surgery, the reduced trauma of minimally invasive interventions combined with initiatives to reduce length of hospital stay and a socioeconomic drive to reduce hospitalisation costs, have all resulted in a trend towards earlier discharge from hospital. There is now a real need for objective, pervasive, and continuous post-operative home recovery monitoring systems. Surgical recovery is a multi-faceted and dynamic process involving biological, physiological, functional, and psychological components. Functional recovery (physical independence, activities of daily living, and mobility) is recognised as a good global indicator of a patient's post-operative course, but has traditionally been difficult to objectively quantify. This thesis outlines the development of a pervasive wireless BSN system to objectively monitor the functional recovery of post-operative patients at home. Biomechanical markers were identified as surrogate measures for activities of daily living and mobility impairment, and an ear-worn activity recognition (e-AR) sensor containing a three-axis accelerometer and a pulse oximeter was used to collect this data. A simulated home environment was created to test a Bayesian classifier framework with multivariate Gaussians to model activity classes. A real-time activity index was used to provide information on the intensity of activity being performed. Mobility impairment was simulated with bracing systems and a multiresolution wavelet analysis and margin-based feature selection framework was used to detect impaired mobility. The e-AR sensor was tested in a home environment before its clinical use in monitoring post-operative home recovery of real patients who have undergone surgery. Such a system may eventually form part of an objective pervasive home recovery monitoring system tailored to the needs of today's post-operative patient.
Supervisor: Darzi, Ara ; Yang, Guang-Zhong Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available