Granger-causality: An efficient single user movement recognition using a smartphone accelerometer sensor

摘要

In this research paper, a novel framework is proposed to classify and analyze human activities. Granger-causality is applied on a smartphone for the recognition of single user activity. It is done in two different ways. In the first one, human activity is recognized on the basis of casual relationships among X-Y-Z Cartesian axes while the second one is based on the casual relationships among the activities. The graphical representation allowed the understanding of mutual dependencies among activities. A tri-axial accelerometer sensor embedded in a smartphone is used to record the acceleration signal. Six human activities successfully classified are walking, walking-upstairs, walking-downstairs, sitting, standing and lying. (C) 2019 Elsevier B.V. All rights reserved.