Using the Blackberry to Assess Mobility for Rehabilitation

Abstract

A Wearable Mobility Monitoring System (WMMS) could be a valuable device for rehabilitation decision-making. This paper presents preliminary research on a proof-ofconcept system that uses the BlackBerry 9550 as a self-contained WMMS platform. Integrated triaxial accelerometer, GPS, and timing data were processed to identify mobility changes-ofstate between standing, walking, sitting, lying, stairs, ramps, riding an elevator, and car riding. This pilot project provides insight into new algorithms and features that can be used to recognize changes-of-state in real-time. Following feature extraction from the sensor data, a decision tree was used to distinguish the change-of-state. In the complete system, real-time change-of-state identification will trigger video capture for improved mobility context analysis. Five trials were collected from one subject while he completed a continuous circuit that incorporated all target mobility tasks. Average sensitivity was 100.00 % and specificity was 86.73 % for walking on level ground and ramps. Sensitivity was 100.00 % and specificity was 98.86 % for stair navigation. These results support continued evaluation of the new WMMS for mobility monitoring.