PLASTIC: Pressure and location-based acoustic sensing touch interface using classification

Abstract

A method is described for developing a pressure sensor panel that uses a single small electromechanical exciter, delivering a sawtooth wave, and a single sensor attached to a panel or structure. A trained classifier is able to recognize the pressure and location of a finger-sized object pressing on the panel based on the characteristics of the waveform detected at the sensor. The classification results of three experiments are reported: 55 virtual buttons on a panel, the pressure classification sensitivity of a single virtual button, and the location classification resolution of a tightly packed grid of points. All three experiments show excellent accuracy (99.7%, 85.2%, 96.0%, respectively) using a simple trained linear SVM classifier with a 70/30 training/validation data ratio, demonstrating that the PLASTIC method is an effective method for classifying the location and pressure of a touch on a panel or structure.