HARMONI: Context-aware Filtering of Sensor Data for Continuous Remote Health Monitoring

A promising architecture for remote healthcare monitoring involves the use of a pervasive device (such as a cellular phone), which aggregates data from multiple body-worn medical sensors and transmits the data to the backend. Unfortunately, the volume of data generated by increasingly sophisticated continuously- active sensors can overwhelm the resources on the mobile device. We propose imbuing the mobile device with the intelligence to perform context-aware filtering of sensor data streams in order to reduce transmissions in cases where the observed data corresponds to the norm expected by the system in a given context. To investigate the efficacy of this technique, we implemented the HARMONI middleware on a mobile device, and used it to collect real sensor data from users. Our experiments demonstrate that context-aware filtering can reduce the uplink bandwidth requirements of the system by up to 72%.

1. Introduction

Remote medical monitoring, particularly of people with chronic diseases such as congestive heart failure or Alzheimer's, is widely viewed as a critical technological innovation for reducing health care delivery costs and improving the responsiveness of medical care. Our focus in this paper is on improving the operational efficiency of the so-called 3-tier remote monitoring architecture [1], [2], where an open, standards-based personal gateway device (such as a PDA or smart phone) is interposed between the body-worn biomedical sensors and the remote backend infrastructure. The gateway device connects to the sensors via a short-range Body Area Network (BAN) technology (e.g., Bluetooth™ or ZigBee™), and uses a second wide-area (WAN) interface (e.g., GPRS or 802.11) to transport the collected sensor data to the backend infrastructure.