FAN, ZHAOPENG,ZHANG, MICHAEL GONG,LIAO, SIMON XIN MENG
申请号：
CA2798337
公开号：
CA2798337A1
申请日:
2012.12.04
申请国别(地区):
CA
年份:
2014
代理人:
摘要：
Factor retrieving is a major approach for pulse wave analysis. Stiffness indexand cardiac outputare widely used factors for cardiac risk detection. Research has been done onclinical pulsewave data which are collected by pulse oximeter. The result shows thatcollected factors have apositive correlation with certain cardiac risks. Some adjustments have beenapplied on thealgorithms that increase the significance. In addition to the factor basedanalysis, other signalprocessing techniques for pulse waveforms are included such as bispectrumestimation, Wavelettransform, and weighted dynamic time warping. Bispectrum estimation andWavelet transformhave meaningful features of pulse waveforms with some special shapes. Weighteddynamic timewarping compares the similarity of waveforms. It also includes medicalsignificance into thecalculation by adjusting the weight vector. This algorithm has higher accuracywhen providingmore samples to compare. The factor based analysis and waveform analysiscompose ananalytic model which can be used for risk evaluation, classification anddisease detection.
