Abstract
A proof-of-concept Wearable Mobility Monitoring System (WMMS) was developed to identify daily activities and provide environmental context, using integrated BlackBerry Smartphone low sensor and video data. Integrated accelerometer data were used to identify mobility changes-of-state (CoS) in real-time, trigger BlackBerry video capture at each CoS, and save activity outcomes on the Smartphone. System evaluation involved collecting WMMS output and (separate) camcorder video under realistic conditions for five able-bodied subjects. The subjects each performed a consecutive series of mobility tasks; including, walking, sitting, lying, stairs, ramps, elevator, bathroom activities, kitchen activities, dining activities and outdoor walking. Activity, timing and contextual information were obtained from the camcorder for comparison. Sensitivity results for sensor-based CoS identification were 97-100% for standing, sitting, lying and taking an elevator; 67-73% for walking-related CoS (stairs, ramps); 40-93% between walking and small movements (brushing teeth, etc.); and below 27% for daily living activities. False positives occurred in less than 12% of all activities, with less than 5% false positives for half the measures. Better classification results were achieved when using both acceleration features and Smartphone integrated video for all activities except sitting. The evaluation demonstrated that the WMMS algorithm and BlackBerry platform were effective for detecting mobility activities, even with low sampling rate sensors. The combined sensor and video analysis enhanced mobility task identification and contextual information.
Highlights
Understanding how people move within their daily lives is important for healthcare decision-making
The participants were asked to follow a predetermined path and perform a series of mobility tasks, including, standing, walking, sitting, riding an elevator, brushing teeth, combing hair, washing hands, drying hands, setting dishes, filling the kettle with water, toasting bread, a simulated meal at a dining table, washing dishes, walking on stairs, lying on Results The results were analyzed in terms of CoS and activity classification
This study demonstrated that BlackBerry accelerometer signal analysis and cell phone video assessment can be combined to identify many mobility activities and the context of these activities
Summary
Understanding how people move within their daily lives is important for healthcare decision-making. A person’s mobility status is self-reported in the clinic, thereby introducing error and increasing the potential for biased information. Functional scales can be administered to help gain an understanding of a person’s mobility status[1,2,3,4]. These tests do not measure how a person moves when leaving the clinic. These phones are multitasking, computing platforms that can incorporate accelerometers, GPS, video camera, light sensors, temperature sensors, gyroscopes, and magnetometers[11,12]. While this study uses a smart phone as the system, the same limitations were encountered with no insight as to how those limitations may be overcome to progress this type of monitoring
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
