On-Line Distinction Methods of Human Falling Motions by Machine Learning(Mechanical Systems)

Abstract

A hip protector system using an airbag for prevention of a femoral neck fracture is under developing. In the system, the instance detection of falling motions by using an appropriate on-line algorithm based on sensor signals is required. The purpose of this paper is to propose on-line distinction procedures of human falling motions based on the machine learning, such as the support vector machine and the neural network. Four distinction procedures of falling motions are proposed in the paper, and the procedures use one axis gyro sensor and two axis accelerometers. Three-types of falling motions which cause a femoral neck fracture for elderly people are considered in the paper. The detection performance of the four procedures are evaluated for the three-types of falling motions, and the procedure based on the neural network considering time series of sensor signals provides 100% detection rate for the three-types of falling motions.