We present a method for measuring gait velocity of older adults using data from existing ambient sensor networks. Gait velocity is an important predictor of fall risk and functional health. In contrast to other approaches that use specific sensors or sensor configurations, our method imposes no constraints on the elderly. We studied different probabilistic models for the modeling of the duration and the distance of the indoor walking paths. Experiments are carried out on 27 months of sensor data and include repeated assessments from an occupational therapist. We showed that gait velocities can be measured with low variance and correlate with most assessments. The advantage of our monitoring system is that because of the continuous measurements, clearer trends can be extracted than from incidental assessments of the occupational therapist.
|Number of pages||11|
|Journal||Journal of ambient intelligence and humanized computing|
|Early online date||28 Feb 2017|
|Publication status||Published - 1 Jun 2018|