Remote patient monitoring service using heterogeneous wireless access networks: architecture and optimization

  • Authors:
  • Dusit Niyato;Ekram Hossain;Sergio Camorlinga

  • Affiliations:
  • School of Computer Engineering, Nanyang Technological University, Singapore;Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, Canada;Department of Radiology and Department of Computer Science, University of Manitoba and TRLabs, Winnipeg, Canada

  • Venue:
  • IEEE Journal on Selected Areas in Communications - Special issue on wireless and pervasive communications for healthcare
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Remote patient monitoring is an eHealth service, which is used to collect and transfer biosignal data from the patients to the eHealth service provider (e.g., healthcare center). A heterogeneous wireless access-based remote patient monitoring system is presented in which multiple wireless technologies are integrated to support continuous biosignal monitoring in presence of patient mobility. A patient-attached monitoring device with a heterogeneous wireless transceiver collects biosignal data from the sensors and transmits the data through the radio access network (RAN) to the eHeath service provider. In this system, the eHealth service provider reserves wireless bandwidth (or connections) from a network service provider in a proactive manner as well as in an on-demand basis. To determine the optimal number of connections to be reserved pro-actively so that the network access cost is minimized, a stochastic programming problem is formulated considering the randomness of service demand due to the mobility of the patients. Since different biosignal data can have different quality-of-service (QoS) requirements, traffic scheduling is used in the patient-attached device which determines whether to transmit and what to transmit over an available wireless connection. To make the optimal scheduling decision, an optimization problem is formulated as a constrained Markov decision process (CMDP). The objective of this formulation is to minimize the connection cost. The proposed system architecture and the optimization formulations will be useful for the eHealth service provider to provide flexible and cost-effective monitoring service to remote/mobile patients.