Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Nonnegative blind source separation fetal heart sound analysis method and device

An analysis method and blind separation technology, applied in image analysis, pulse/heart rate measurement, image data processing, etc., can solve the problems of difficult detection of autocorrelation function waveforms, achieve high accuracy, good clinical fetal heart rate monitoring, and rapid extraction Effect

Active Publication Date: 2016-07-20
GUANGDONG UNIV OF TECH
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the processing object of the correlation method is mainly deterministic periodic signals, and the fetal heart sound signal is affected by the fetus itself and its surrounding environment, it is not a deterministic periodic signal. This random change in cycle and waveform makes it difficult to detect the autocorrelation function waveform.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Nonnegative blind source separation fetal heart sound analysis method and device
  • Nonnegative blind source separation fetal heart sound analysis method and device
  • Nonnegative blind source separation fetal heart sound analysis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be further described below in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0052] Such as figure 1 As shown, a non-negative blind separation fetal heart sound analysis method comprises the following steps:

[0053] 1) collecting fetal heart sound signals;

[0054] 2 pairs figure 2 The fetal heart sound signal collected in the computer is preprocessed, and the preprocessing process adopts wavelet transform that can effectively remove noise and maintain the local singularity of the signal;

[0055] 3) Transform the preprocessed signal into the time-frequency domain to obtain a non-negative spectrum. The method used is: calculate the wigner-ville distribution of the preprocessed signal and obtain its amplitude spectrum as Figure 4 ;

[0056] 4) Use non-negative matrix decomposition to perform blind separation, process the amplitude spectrum of the fetal heart sound signa...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a nonnegative blind source separation fetal heart sound analysis method and device. The method comprises the following steps: 1) collecting fetal heart sound signals; 2) carrying out pretreatment on the collected fetal heart sound signals, and adopting wavelet transform, which not only can effectively remove noise, but also can keep local singularity of the signals, in the pretreatment process; 3) converting the signals obtained after pretreatment to a time-frequency domain to obtain nonnegative frequency spectrum, the adopted method being: carrying out wigner-ville distribution calculating on the signals obtained after pretreatment and carrying out modulus calculating to obtain magnitude spectrum; 4) carrying out blind source separation by utilizing non-negative matrix factorization and carrying out processing on the fetal heart sound signal amplitude spectrum to obtain nonnegative time-frequency component of the fetal heart sound signal; 5) drawing an envelope curve; and 6) analyzing the envelope, setting dual thresholds to realize envelope segmentation and calculating instantaneous heart rate. The analysis method and device are good in flexibility, can segment the fetal heart sound signal accurately, and are high in instantaneous heart rate identification accuracy.

Description

technical field [0001] The invention relates to a non-negative blind separation fetal heart sound analysis method and device, belonging to the technical field of medical devices, in particular to the technical field of fetal monitoring. Background technique [0002] Most fetal dysplasia and even fetal asphyxia are caused by distress in the mother's womb. Monitoring the fetus in the mother's body during the perinatal period is an important means to ensure the safety of the fetus and the mother, and to achieve national eugenics. Since the heart sound is a reflection of the mechanical movement of the heart and large blood vessels, before some cardiovascular diseases have developed enough to produce pathological changes and clinical symptoms, the murmurs and distortions in the heart sound have already indicated the occurrence of the disease. Analytics can enable early diagnosis and intervention of diseases. The analysis of fetal heart sound signal is an important means of fetal...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/00G06T5/00A61B8/02
CPCG06T7/0012A61B8/02G06T2207/30044G06T2207/30048G06T5/70
Inventor 谢胜利谢侃蔡坤刘辉
Owner GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products