A Novel Beat Detection Method for Blood Pressure Signals Using Slope Sum Mean Shift Technology

In this paper, a novel slope sum mean shift method for beat detection of blood pressure signals is presented. The method consists of three components: a windowed and weighted slope sum function (SSF), the mean shift algorithm and the peak position calibration procedure. The slope sum function is used to extract and magnify the ABP waveform features while reduce the computation efficiency for mean shift algorithm. The mean shift algorithm is then applied to find the maxima of the blood pressure signals, and finally the peak position calibration procedure is used for correcting the errors of peak position shift brought by previous two steps. Experiment results showed its accuracy and efficiency in beat detection for blood pressure signals.