Abstract

Info

Title:: Gaussian mixture model-based method for extracting the features of pulse wave

Author(s):: SU Zhigang1; 2; ZHU Hailing1; HAO Jingtang2; 1. Tianjin Key Lab for Advanced Signal and Image Processing, Civil Aviation University of China, Tianjin 300300, China; 2. Sino-European Institute of Aviation Engineering, Civil Aviation University of China, Tianjin 300300, China

Keywords:: ; Keywords: pulse wave; blood pressure measurement; Gaussian mixture model; feature extraction; Taylor series

Abstract:: Abstract: The features of pulse wave reflect the physiological and pathological states of human body. A method based on Gaussian mixture model was proposed for the feature extraction of pulse wave. In this method, the number and type of pulse wave feature points were determined by the zero point of the first difference signal and the second difference signal of pulse wave, and the complexity of the location estimation of the feature point was simplified by Taylor series expansion. The simulated and actual data processing results showed that the proposed method acquired the location and information of pulse wave feature points more accurately as comparison with classic algorithms. The proposed method is an effective method for the feature extraction of pulse wave.