Statistical approaches for personal feature extraction from pressure array sensors

We propose two statistical probability approaches to extract personal feature from the user's grip force data. One approach is based on grip force changes predicted by the Kalman filter, the other is based on distributions of grip force changes by Jensen-Shannon(JS) divergence. Personal feature is the customary behavior that repeatedly appears without the user being aware of it. The personal feature is used for not only user-authentication, but also user-special commands. We mount pressure array sensors on a mobile phone and show that our proposals can extract personal feature from the user's grip force data with 10[%] error in FAR-FRR by the Kalman filter approach and the accuracy of 100[%] by the JS divergence approach.