Detection of Various Postures and Gait Using a Wearable Triaxial Accelerometer

Abstract

The purpose of this study was to examine whether various postures and gait can be determined using a wearable triaxial accelerometer under simulated hospital conditions. [Subjects and Methods] Ten healthy adults were recruited for this study. A triaxial accelerometer was attached to their left thorax. The experimental tasks were: 1) the basic postures of supine, sitting and standing, 2) changing the reclining angle while lying in a bed, and 3) walking and moving in a wheelchair. [Results] The Y-axis accelerations of sitting, standing and lying in bed with a reclination angle > 60 degrees were lower than that of the lying posture. The triaxial composite acceleration during walking was higher than that of moving a wheelchair, and increased as the walking speed increased. [Conclusion] An upright posture could be determined by a Y-axis acceleration of less than-0.7 G, and walking and wheelchair movement could be determined by a triaxial composite acceleration of more than 1.3 G.

Development of Invisible Sensors and a Machine-Learning-Based Recognition System Used for Early Prediction of Discontinuous Bed-Leaving Behavior Patterns

“…Kawamura et al [5] proposed a wearable sensor system using a three-axis accelerometer. For their system, unrestrained measurements are actualized using a lightweight sensor module of 13 g. With consideration of clinical applications, they obtained not only metaparameters that contributed to recognition, but also experimentally obtained results with bed-up and wheelchair locomotion.…”