Bayesian classification of acoustical waveforms under environmental variability
Designing ergonomic interfaces for man-machine interaction is a major task for today's computer design engineers. A new type of tangible man-machine communication interface which is based on acoustics is presented in this paper. The proposed new approach is the use of pattern recognition to match the pattern of a received signal's feature with a template, acquired during a learning stage, associated with a predefined location. Theoretically this method, referred as Location Patten Matching (LPM) can work on heterogeneous medium of any shape or material using one or two sensors. Therefore they overcome the limitations of the more widely used approaches based on Time Delay Of Arrival (TDOA).