Home › Publications

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

Sun, 07/04/2010 - 02:10 — AdrianFreed
TitleSupport Vector Machine Learning for Gesture Signal Estimation with a Piezo Resistive Fabric Touch Surface
Publication TypeConference Paper
Year of Publication2010
AuthorsSchmeder, Andrew, and Freed Adrian
Conference NameNIME
Conference LocationSydney, Australia
AbstractThe 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.