Feature extraction and recognition methods based on phonocardiogram

One-dimensional heart sounds signal is converted into two-dimensional phonocardiogram (2D-PCG), then extracts image feature of heart sounds based on image processing technology in a 2D-PCG. Firstly we realize the wavelet noise reduction and amplitude normalization of one-dimensional heart sounds by...

Full description

Saved in:
Bibliographic Details
Published in2016 Third International Conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC) pp. 87 - 92
Main Authors Xiefeng Cheng, Kexue Sun, Xuejun Zhang, Chenjun She
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2016
Subjects
2D-PCG
degree of heart sound signal certainty
Feature extraction
Fingerprint recognition
Heart
Noise reduction
Phonocardiography
Physiology
recognition
sequence code of inflection point
Online AccessGet full text

Cover

More Information
Summary:One-dimensional heart sounds signal is converted into two-dimensional phonocardiogram (2D-PCG), then extracts image feature of heart sounds based on image processing technology in a 2D-PCG. Firstly we realize the wavelet noise reduction and amplitude normalization of one-dimensional heart sounds by one-dimensional signal processing method, and then convert Heart sounds into 2D-PCG with uniformity and comparability, and pretreatment. And analyze the image features of 2D-PCG which is characterization of Heart sounds' physiological information combining with heart sounds' physiological significance and 2D-PCG's image features, focus on vertical and horizontal ratio of coordinate and sequence code of inflection point. In order to quickly classify the heart sound signal, the paper introduces the new concept: degree of heart sound signal certainty (HSSCD). Finally, efficiency and feasibility are verified through the heart sound acquisition, classification and identification experiments. At last, explore the feasibility of classification and identification of 2D-PCG using Euclidean distance and degree of heart sound signal certainty based on vertical and horizontal ratio of coordinate and sequence code of inflection point and wavelet coefficients. Experimental results show that the three features can achieve the classification and recognition of the 2D-PCG, and inflection point sequence code gets the highest recognition rate. The method of 2D-PCG classification and identification based on a two-image processing has the feasibility and practical applicability, and has broad application prospects.
DOI:10.1109/DIPDMWC.2016.7529369