CLASSIFICATION OF PHOTOPLETHYSMOGRAPHIC SIGNALS USING SUPPORT VECTOR MACHINES FOR VASCULAR RISK ASSESSMENT

摘要

Cardiovascular diseases have registered a high rate ofmorbidity and mortality in the world, therefore theassessment of cardiovascular risk in human beings is ofprime importance. In this paper Photoplethysmographic(PPG) signals recorded from 60 subjects have beenclassified as ?normal? or ?at risk?. In this process, we haveused an Auto-Regressive eXogenous input (ARX) linearparametric model for extracting features that represent thecirculatory system and a support vector machine (SVM)for classifying the signals based on the four data segmentselection policies; best fit, three best fit, ten best fit andaverage best fit. The classification method employed inthis work appears to be novel. According to thesensitivity and the specificity obtained (84.615% and92.31%, respectively), the average best fit policy waschosen as the best policy for the classification of PPGsignals.