An adaptive prediction method for signal fusion.

Abstract

Many biomedical signal processing applications include the significant challenge of sensor data fusion. In this work, an adaptive prediction method fuses a relatively higher bandwidth, lower absolute accuracy (fast) signal with a relatively lower bandwidth, higher absolute accuracy (accurate) signal of the same quantity into a combined signal that is both fast and accurate. Iterative estimates of model parameters minimize a regularized mean square prediction error that arises from using the fast signal to predict the accurate signal. We illustrate the method by fusing a lower bandwidth porcine thermal dilution cardiac output signal with a relatively higher bandwidth, less accurate peripheral arterial pressure pulse contour cardiac output signal. The combined cardiac output signal has both thermal dilution accuracy and pulse contour bandwidth.