Fall detection by built-in tri-accelerometer of smartphone

In this study, a fall detection system based on the data acquired from a waist-mounted smartphone has been developed in a real-time environment. The built-in tri-accelerometer was utilized to collect the information about body movement. At the same time, the smartphone is able to classify the data for activity recognition. Body motion can be classified into five different patterns, i.e. vertical activity, lying, sitting or static standing, horizontal activity and fall. If a fall is suspected, an automatic Multimedia Messaging Service (MMS) will be sent to pre-selected people, with information including the time, GPS coordinate, and Google map of suspected fall location. The major advantage of the proposed system is the use of smartphone which is readily available to most people.