Reliable and practical fall prediction using artificial neural network

The growing elder population has inspired remarkable research in the prevention of fall injuries. A reliable technique to predict fall incidence, along with a corresponding mobile phone app, is proposed in this paper. The technique combines the benefits of traditional medical history based paradigm and non-historical paradigm. The app analyzes single leg motion to predict if the carrying individual is about to fall with a desirably practical alert time, not too long like in the medical history based paradigm, not too short like in the non-historical paradigm. Furthermore, this approach utilizes leg motion instead of torso motion to gain considerable longer alert time. This fall prediction technique will be a perfect fit into a real time automated system for fall prevention.