Automated patient handling activity recognition for at-risk caregivers using an unobtrusive wearable sensor

Abstract

Patient handling activities with awkward postures expose healthcare providers to a high risk of overexertion injury. The recognition of patient handling activities (PHA) is the first step to reduce injury risk for caregivers. In this paper, we propose a system to solve the problem, which comprises an unobtrusive wearable device and a novel spatio-temporal warping (STW) pattern recognition framework. The wearable device, named Smart Insole 2.0, is equipped with a rich set of sensors and can capture the information of patient handling activities. The STW pattern recognition framework fully exploits the spatial and temporal characteristics of plantar pressure, to quantify the similarity for the purpose of activity recognition. we perform a pilot study with eight subjects, including eight common activities in a nursing room. The experimental results show the overall classification accuracy achieves 91.7%. Meanwhile, the qualitative profile and load level can also be classified with accuracies of 98.3% and 92.5%, respectively.