Hidden Markov models implementation for tangible interfaces

Smart objects equipped with inertial sensors can recognize gestures and act as tangible interfaces to interact with smart environments. Hidden Markov Models (HMM) are a powerful tool for gesture recognition. Gesture recognition with HMM is performed using the forward algorithm. In this paper, we evaluate the fixed point implementation of the forward algorithm for HMM to assess if this implementation can be effective on resource constraint devices such as the Smart Micrel Cube (SMCube). The SMCube is a tangible interface that embeds an 8-bit microcontroller running at 7.372 MHz. The complexity-performance trade-off has been explored, and a discussion on the critical steps of the algorithm implementation is presented.