Recognition of direction of fall by smartphone

In this paper we enhance our fall monitor with our recognition of the direction of fall functionality. We not only analyze the change of acceleration but also analyze five typical actions of humans: walking, running, standing up, sitting down and jumping. Then we compare these actions with the acceleration characteristics of a fall: the weightlessness, the impact, and the overturning of the body. Because the waist is the center of gravity in the human body, our system is used more effectively when we place the smart phone at the waist. We also analyze the three different accelerations in space to infer the fall direction of the user. Our system is based both on an open source system platform and on the accelerometer in the smart phone.