The long term objective of this project is to enable elderly persons to independently live within their own homes later into their lives with the assurance that their safety and well-being can be remotely monitored by health care professionals. A critical component of remote health care monitoring is physically tracking the location of the patient within a living environment and assessing the patient's mobility. Research has shown that mobility, which includes gait characteristics, is integrally related to patient health and changes in mobility can be an indicator of cognitive and/or physical decline. Positional tracking and mobility information can be further used to estimate clinically relevant activities of daily living, which are also useful in assessing patient health. The objective of this STTR is to research and develop a Position Tracking and Mobility Assessment System targeted specifically for elderly patients within their home environment. The eventual system will be low-cost, accurate, unobtrusive, and simple to install.
The specific aims of phase 1 are to perform the research necessary to demonstrate two configurations or modes of the system: Tag-Based Tracking that relies on the patient(s) wearing a tiny wireless transceiver about the size of a quarter, and Tag-Free Tracking that will enable position and velocity tracking even when a patient is not carrying a tracking tag. Both modes make use of low-power wireless technology and changes in receive-signal-strength-indicator (RSSI), which indicates distance between a transmitter and a receiver. Position tracking for the Tag-Based Tracking will be performed by probabilistic inference using multiple RSSI measurements between the tag and small transceivers mounted on walls of the home. Position tracking will be augmented by fusing RSSI data with digital compass and accelerometer data. The Tag-Free Tracking will be for single-patient monitoring conditions and if successful will provide a unique solution that mitigates a critical compliance risk regarding patient failure to wear the tags. Tracking is again achieved using RSSI data and the hardware installation within the home is identical to the tag-based tracking. However, the tag-free method relies only on wall-mounted transceivers to detect changes in RSSI measurements affected by reflections and absorption off of the patient moving within a room. The Position Tracking and Mobility Assessment System will be designed using the wireless platform engineered by EmbedRF LLC - the industry partner for this project. Work on the tracking algorithms will be performed by researchers at the Oregon Health &Sciences University - the academic/research partner. Phase 1 will involve research to demonstrate feasibility of the technology, and producing prototype systems for evaluation at the OHSU point-of-care lab. Phase 2 efforts will include hardware modifications and algorithm design to improve both tracking performance and the detection of other aspects of mobility. Phase 2 will also involve further commercialization efforts and development of the remote monitoring and notification system for use by health-care professionals, and include a more extensive clinical evaluation within peoples'homes.
The ability to move is a critical function that underlies the quality of life of elders. In addition, changes in aspects of mobility such as speed of walking and stride length have been shown to correlate with changes in physical and cognitive function. Development of a low cost system for unobtrusive position tracking and mobility assessment will allow elders to continue independent living within their homes while knowing that health care providers are monitoring their well-being over time or should an emergency arise.
| Schafermeyer, Erich R; Wan, Eric A; Samin, Shadman et al. (2015) Multi-resident identification using device-free IR and RF fingerprinting. Conf Proc IEEE Eng Med Biol Soc 2015:5481-4 |
| Jacobs, Peter G; Wan, Eric A; Schafermeyer, Erich et al. (2014) Measuring in-home walking speed using wall-mounted RF transceiver arrays. Conf Proc IEEE Eng Med Biol Soc 2014:914-7 |
| Paul, Anindya S; Wan, Eric A; Adenwala, Fatema et al. (2014) MobileRF: A Robust Device-Free Tracking System Based On a Hybrid Neural Network HMM Classifier. Proc ACM Int Conf Ubiquitous Comput 2014:159-170 |
