Support Vector Machine Learning for Gesture Signal Estimation with a Piezo Resistive Fabric Touch Surface

Title	Support Vector Machine Learning for Gesture Signal Estimation with a Piezo Resistive Fabric Touch Surface
Publication Type	Conference Paper
Year of Publication	2010
Authors	Schmeder, Andrew [1], and Freed Adrian [2]
Conference Name	NIME
Conference Location	Sydney, Australia
Abstract	The design of an unusually simple fabric-based touch and pressure sensor is introduced. An analysis of the raw sensor data is shown to have significant non-linearities and non-uniform noise. Using support vector machine learning and a state-dependent adaptive filter it is demonstrated that these problems can be overcome. The method is evaluated quantitatively using a statistical estimate of the instantaneous rate of information transfer. The SVM regression alone is shown to improve the gesture signal information rate by up to 20% with zero added latency, and in combination with filtering by 40% subject to a constant latency bound of 10 milliseconds.